Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2601 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0134. Min Range: -10.0134
Max Act: 10.0134. Min Act: -0.1700
Data Index: 2482280 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.8884. Min Act: -0.1700
Data Index: 3803286 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.7634. Min Act: -0.1700
Data Index: 6708645 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.7009. Min Act: -0.1700
Data Index: 3363633 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.4509. Min Act: -0.1700
Data Index: 5603981 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.3884. Min Act: -0.1700
Data Index: 3404688 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.3884. Min Act: -0.1700
Data Index: 6537106 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.3259. Min Act: -0.1700
Data Index: 3388553 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.2634. Min Act: -0.1700
Data Index: 1352402 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.2009. Min Act: -0.1700
Data Index: 1465349 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.2009. Min Act: -0.1700
Data Index: 1656317 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.1384. Min Act: -0.1700
Data Index: 7292877 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.0759. Min Act: -0.1700
Data Index: 8817578 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.0134. Min Act: -0.1700
Data Index: 2686708 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.0134. Min Act: -0.1700
Data Index: 7415755 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.0134. Min Act: -0.1700
Data Index: 4843982 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0134. Min Range: -10.0134
Max Act: 8.9509. Min Act: -0.1700
Data Index: 6825332 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.0134. Min Act: -0.1700
Data Index: 5253528 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0134. Min Range: -10.0134
Max Act: 9.0134. Min Act: -0.1700
Data Index: 5749795 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0134. Min Range: -10.0134
Max Act: 8.9509. Min Act: -0.1700
Data Index: 7025756 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19