Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 95 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.2813. Min Act: -0.1700
Data Index: 521105 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.1875. Min Act: -0.1700
Data Index: 6468786 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.1563. Min Act: -0.1700
Data Index: 3533394 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.1875. Min Act: -0.1700
Data Index: 2817631 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.1250. Min Act: -0.1700
Data Index: 8626653 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.0938. Min Act: -0.1700
Data Index: 3557346 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.0625. Min Act: -0.1700
Data Index: 1980083 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.0625. Min Act: -0.1700
Data Index: 209096 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.0625. Min Act: -0.1700
Data Index: 1041849 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.0312. Min Act: -0.1700
Data Index: 8107073 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.0000. Min Act: -0.1700
Data Index: 3440124 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.0312. Min Act: -0.1700
Data Index: 3985806 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.0000. Min Act: -0.1700
Data Index: 3330969 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2813. Min Range: -4.2813
Max Act: 3.9687. Min Act: -0.1700
Data Index: 4124786 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.0000. Min Act: -0.1700
Data Index: 8627708 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.0000. Min Act: -0.1700
Data Index: 3371662 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2813. Min Range: -4.2813
Max Act: 4.0000. Min Act: -0.1700
Data Index: 733539 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2813. Min Range: -4.2813
Max Act: 3.9687. Min Act: -0.1700
Data Index: 1785326 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2813. Min Range: -4.2813
Max Act: 3.9687. Min Act: -0.1700
Data Index: 8281843 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2813. Min Range: -4.2813
Max Act: 3.9375. Min Act: -0.1700
Data Index: 7898704 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19