Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.8643. Min Act: -0.1700
Data Index: 2015718 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.8018. Min Act: -0.1700
Data Index: 6385474 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.8643. Min Act: -0.1700
Data Index: 5099964 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.5518. Min Act: -0.1695
Data Index: 7895215 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.4893. Min Act: -0.1700
Data Index: 4116396 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.4268. Min Act: -0.1699
Data Index: 7475607 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.3643. Min Act: -0.1700
Data Index: 7351235 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.3643. Min Act: -0.1700
Data Index: 6212077 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.3643. Min Act: -0.1700
Data Index: 8343609 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.3643. Min Act: -0.1700
Data Index: 1474583 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.3018. Min Act: -0.1699
Data Index: 4440140 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.3018. Min Act: -0.1700
Data Index: 3156115 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.3643. Min Act: -0.1700
Data Index: 5830515 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.3643. Min Act: -0.1700
Data Index: 2817334 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.2393. Min Act: -0.1700
Data Index: 3920853 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.2393. Min Act: -0.1687
Data Index: 332883 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.1768. Min Act: -0.1700
Data Index: 2975310 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.2393. Min Act: -0.1699
Data Index: 357982 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.2393. Min Act: -0.1700
Data Index: 1644429 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8643. Min Range: -9.8643
Max Act: 9.1768. Min Act: -0.1698
Data Index: 7735332 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19