Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2915. Min Range: -6.2915
Max Act: 6.2915. Min Act: -0.1700
Data Index: 2927094 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2915. Min Range: -6.2915
Max Act: 6.1977. Min Act: -0.1700
Data Index: 7554936 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2915. Min Range: -6.2915
Max Act: 6.0727. Min Act: -0.1700
Data Index: 6469114 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2915. Min Range: -6.2915
Max Act: 6.0727. Min Act: -0.1700
Data Index: 7624039 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2915. Min Range: -6.2915
Max Act: 6.0415. Min Act: -0.1700
Data Index: 6637780 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2915. Min Range: -6.2915
Max Act: 6.0415. Min Act: -0.1700
Data Index: 8722665 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.9790. Min Act: -0.1700
Data Index: 1116782 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.9790. Min Act: -0.1700
Data Index: 6364447 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.9477. Min Act: -0.1700
Data Index: 400597 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.9165. Min Act: -0.1700
Data Index: 3405770 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.8852. Min Act: -0.1700
Data Index: 2375868 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.8852. Min Act: -0.1700
Data Index: 8739884 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.8852. Min Act: -0.1700
Data Index: 3484075 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.8852. Min Act: -0.1700
Data Index: 526866 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.8540. Min Act: -0.1700
Data Index: 2735883 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.8540. Min Act: -0.1700
Data Index: 6531786 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.8540. Min Act: -0.1700
Data Index: 6660453 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.8227. Min Act: -0.1700
Data Index: 1976009 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.8227. Min Act: -0.1700
Data Index: 4061244 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2915. Min Range: -6.2915
Max Act: 5.8227. Min Act: -0.1700
Data Index: 3640954 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19