Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.5693. Min Act: -0.1700
Data Index: 4422046 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.5068. Min Act: -0.1700
Data Index: 6967367 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.5693. Min Act: -0.1700
Data Index: 8571321 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.4755. Min Act: -0.1700
Data Index: 2346911 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.4755. Min Act: -0.1700
Data Index: 3298861 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.4443. Min Act: -0.1700
Data Index: 5906761 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.4130. Min Act: -0.1700
Data Index: 6987054 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.3505. Min Act: -0.1700
Data Index: 7682250 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.3818. Min Act: -0.1700
Data Index: 8803906 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.3505. Min Act: -0.1700
Data Index: 4303455 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.3193. Min Act: -0.1700
Data Index: 6987052 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.2880. Min Act: -0.1700
Data Index: 5849617 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.2255. Min Act: -0.1700
Data Index: 5118882 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.2255. Min Act: -0.1700
Data Index: 6153108 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.2255. Min Act: -0.1700
Data Index: 1906589 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.2255. Min Act: -0.1700
Data Index: 998684 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.2255. Min Act: -0.1700
Data Index: 6243593 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.1943. Min Act: -0.1700
Data Index: 4530228 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.1630. Min Act: -0.1700
Data Index: 1441854 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5693. Min Range: -4.5693
Max Act: 4.1630. Min Act: -0.1700
Data Index: 6010889 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19