Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4327 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 16.3643. Min Range: -16.3643
Max Act: 16.3643. Min Act: -0.1700
Data Index: 6791624 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.3643. Min Range: -16.3643
Max Act: 16.3643. Min Act: -0.1700
Data Index: 8831978 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.3643. Min Range: -16.3643
Max Act: 16.3643. Min Act: -0.1700
Data Index: 7108818 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.3643. Min Range: -16.3643
Max Act: 16.1143. Min Act: -0.1700
Data Index: 3608732 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.3643. Min Range: -16.3643
Max Act: 16.1143. Min Act: -0.1700
Data Index: 3053033 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.8643. Min Act: -0.1700
Data Index: 4598894 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.9893. Min Act: -0.1700
Data Index: 577432 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.8643. Min Act: -0.1700
Data Index: 6788832 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.8643. Min Act: -0.1700
Data Index: 3748063 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.8643. Min Act: -0.1700
Data Index: 3683733 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.8643. Min Act: -0.1700
Data Index: 2376474 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.8643. Min Act: -0.1700
Data Index: 2928212 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.8018. Min Act: -0.1700
Data Index: 1325459 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.8018. Min Act: -0.1700
Data Index: 8477018 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.8643. Min Act: -0.1700
Data Index: 1857684 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.7393. Min Act: -0.1700
Data Index: 6573948 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.8643. Min Act: -0.1700
Data Index: 7054016 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.8018. Min Act: -0.1700
Data Index: 8788556 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.7393. Min Act: -0.1700
Data Index: 7344000 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.3643. Min Range: -16.3643
Max Act: 15.7393. Min Act: -0.1700
Data Index: 2646675 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19