Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 30 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.9700. Min Act: -0.1700
Data Index: 2177250 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.9383. Min Act: -0.1700
Data Index: 2051592 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.9383. Min Act: -0.1700
Data Index: 8475090 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.9066. Min Act: -0.1700
Data Index: 3098422 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.9066. Min Act: -0.1700
Data Index: 4961030 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.9066. Min Act: -0.1700
Data Index: 4866201 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8749. Min Act: -0.1700
Data Index: 5487738 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8749. Min Act: -0.1700
Data Index: 8082066 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8908. Min Act: -0.1700
Data Index: 3825123 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8590. Min Act: -0.1700
Data Index: 99840 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8590. Min Act: -0.1700
Data Index: 5646264 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8749. Min Act: -0.1700
Data Index: 2167450 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8431. Min Act: -0.1700
Data Index: 3585171 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8272. Min Act: -0.1700
Data Index: 5992927 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8272. Min Act: -0.1700
Data Index: 5117520 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8113. Min Act: -0.1700
Data Index: 60033 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8431. Min Act: -0.1700
Data Index: 4216598 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8113. Min Act: -0.1700
Data Index: 6739719 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.7954. Min Act: -0.1700
Data Index: 3292681 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9700. Min Range: -2.9700
Max Act: 2.8113. Min Act: -0.1700
Data Index: 776555 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19