Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5518 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2875. Min Range: -8.2875
Max Act: 8.2875. Min Act: -0.1700
Data Index: 1420130 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.6625. Min Act: -0.1700
Data Index: 4569633 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.4125. Min Act: -0.1700
Data Index: 8268099 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.2875. Min Act: -0.1700
Data Index: 7043381 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.2562. Min Act: -0.1700
Data Index: 7069882 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.2562. Min Act: -0.1700
Data Index: 5214108 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.2250. Min Act: -0.1700
Data Index: 2839349 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.2250. Min Act: -0.1700
Data Index: 4337120 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.1312. Min Act: -0.1700
Data Index: 5725754 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.1312. Min Act: -0.1700
Data Index: 934095 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.1937. Min Act: -0.1700
Data Index: 4702281 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.1937. Min Act: -0.1700
Data Index: 3361240 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.1312. Min Act: -0.1700
Data Index: 7322812 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.1000. Min Act: -0.1700
Data Index: 3909898 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.1000. Min Act: -0.1700
Data Index: 6452000 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.0687. Min Act: -0.1700
Data Index: 8454693 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.0687. Min Act: -0.1700
Data Index: 4337175 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.0375. Min Act: -0.1700
Data Index: 2343988 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.0375. Min Act: -0.1700
Data Index: 3424155 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2875. Min Range: -8.2875
Max Act: 7.0375. Min Act: -0.1700
Data Index: 2583468 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19