Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2591 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.8791. Min Act: -0.1700
Data Index: 3424925 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.8791. Min Act: -0.1700
Data Index: 684322 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.8791. Min Act: -0.1700
Data Index: 8098955 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.8478. Min Act: -0.1700
Data Index: 6104659 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.8478. Min Act: -0.1700
Data Index: 6455241 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.8478. Min Act: -0.1700
Data Index: 5434512 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.8791. Min Act: -0.1700
Data Index: 4576415 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.7853. Min Act: -0.1700
Data Index: 6363391 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.8166. Min Act: -0.1700
Data Index: 6560536 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.8478. Min Act: -0.1700
Data Index: 1177127 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.8166. Min Act: -0.1700
Data Index: 587018 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.8166. Min Act: -0.1700
Data Index: 2172775 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.8166. Min Act: -0.1700
Data Index: 2230548 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.7853. Min Act: -0.1700
Data Index: 4089178 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.7540. Min Act: -0.1700
Data Index: 7672868 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.7853. Min Act: -0.1700
Data Index: 1701092 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.7853. Min Act: -0.1700
Data Index: 6697904 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.7227. Min Act: -0.1700
Data Index: 6458208 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.7227. Min Act: -0.1700
Data Index: 1101449 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8791. Min Range: -3.8791
Max Act: 3.7227. Min Act: -0.1700
Data Index: 7421737 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19