Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4117. Min Range: -9.4117
Max Act: 9.4117. Min Act: -0.1700
Data Index: 3276359 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4117. Min Range: -9.4117
Max Act: 9.1617. Min Act: -0.1700
Data Index: 4768936 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4117. Min Range: -9.4117
Max Act: 9.0367. Min Act: -0.1700
Data Index: 1840959 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.9742. Min Act: -0.1700
Data Index: 6737688 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.9742. Min Act: -0.1700
Data Index: 8334666 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.8492. Min Act: -0.1700
Data Index: 4754797 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.7867. Min Act: -0.1700
Data Index: 6070321 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.7242. Min Act: -0.1700
Data Index: 1237710 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.6617. Min Act: -0.1700
Data Index: 7598073 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.6617. Min Act: -0.1700
Data Index: 2164086 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.6617. Min Act: -0.1700
Data Index: 7649966 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.6617. Min Act: -0.1700
Data Index: 8336567 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.5992. Min Act: -0.1700
Data Index: 7955347 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.5992. Min Act: -0.1700
Data Index: 8552300 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.5367. Min Act: -0.1700
Data Index: 3533254 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.5367. Min Act: -0.1700
Data Index: 5666859 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.5367. Min Act: -0.1700
Data Index: 744631 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.5367. Min Act: -0.1700
Data Index: 6819383 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.5367. Min Act: -0.1700
Data Index: 7448829 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4117. Min Range: -9.4117
Max Act: 8.4117. Min Act: -0.1700
Data Index: 2623168 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19