Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3774 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.5348. Min Act: -0.1700
Data Index: 1102698 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.4722. Min Act: -0.1700
Data Index: 1273794 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.3154. Min Act: -0.1700
Data Index: 122022 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.2840. Min Act: -0.1700
Data Index: 6080953 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.2683. Min Act: -0.1700
Data Index: 4764569 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.2368. Min Act: -0.1700
Data Index: 3256911 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.2211. Min Act: -0.1700
Data Index: 3683671 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.2368. Min Act: -0.1700
Data Index: 7204858 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.2211. Min Act: -0.1700
Data Index: 6349259 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.2054. Min Act: -0.1700
Data Index: 3798633 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.2054. Min Act: -0.1700
Data Index: 682622 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.2211. Min Act: -0.1700
Data Index: 4152182 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.2211. Min Act: -0.1700
Data Index: 1488530 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.2054. Min Act: -0.1700
Data Index: 5489006 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.1897. Min Act: -0.1700
Data Index: 8527733 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.1897. Min Act: -0.1700
Data Index: 1584342 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.1897. Min Act: -0.1700
Data Index: 3557856 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.1897. Min Act: -0.1700
Data Index: 2474000 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.1739. Min Act: -0.1700
Data Index: 3660100 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5348. Min Range: -3.5348
Max Act: 3.1897. Min Act: -0.1700
Data Index: 3503997 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19