Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.6121. Min Act: -0.1700
Data Index: 6332458 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.4871. Min Act: -0.1700
Data Index: 7122769 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.4871. Min Act: -0.1700
Data Index: 5878195 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.4871. Min Act: -0.1700
Data Index: 967887 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.3933. Min Act: -0.1700
Data Index: 8612813 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.3933. Min Act: -0.1700
Data Index: 2116176 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.3621. Min Act: -0.1700
Data Index: 4369661 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.3621. Min Act: -0.1700
Data Index: 4609666 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.3308. Min Act: -0.1700
Data Index: 27765 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.3308. Min Act: -0.1700
Data Index: 7470748 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.2996. Min Act: -0.1700
Data Index: 3303079 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.2996. Min Act: -0.1700
Data Index: 7372242 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.2996. Min Act: -0.1700
Data Index: 8317068 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.2996. Min Act: -0.1700
Data Index: 3791781 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.2996. Min Act: -0.1700
Data Index: 8653821 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.2996. Min Act: -0.1700
Data Index: 2525468 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.2683. Min Act: -0.1700
Data Index: 1635144 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.2683. Min Act: -0.1700
Data Index: 6152284 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.2683. Min Act: -0.1700
Data Index: 1867125 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6121. Min Range: -4.6121
Max Act: 4.2371. Min Act: -0.1700
Data Index: 8318514 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19