Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1099 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0234. Min Range: -5.0234
Max Act: 5.0234. Min Act: -0.1700
Data Index: 10240 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0234. Min Range: -5.0234
Max Act: 5.0234. Min Act: -0.1700
Data Index: 6725652 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0234. Min Range: -5.0234
Max Act: 5.0234. Min Act: -0.1700
Data Index: 5937941 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0234. Min Range: -5.0234
Max Act: 5.0234. Min Act: -0.1700
Data Index: 2136170 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0234. Min Range: -5.0234
Max Act: 5.0234. Min Act: -0.1700
Data Index: 6417043 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.9921. Min Act: -0.1700
Data Index: 7774532 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.9921. Min Act: -0.1700
Data Index: 3730030 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.9609. Min Act: -0.1700
Data Index: 3081848 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.9296. Min Act: -0.1700
Data Index: 2687657 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.9609. Min Act: -0.1700
Data Index: 5337440 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.9609. Min Act: -0.1700
Data Index: 2817700 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.9296. Min Act: -0.1700
Data Index: 952612 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.9296. Min Act: -0.1700
Data Index: 6781800 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.9296. Min Act: -0.1700
Data Index: 2847435 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.8984. Min Act: -0.1700
Data Index: 5860099 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.8984. Min Act: -0.1700
Data Index: 7657682 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.8359. Min Act: -0.1700
Data Index: 1487164 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.8671. Min Act: -0.1700
Data Index: 6858876 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.8984. Min Act: -0.1700
Data Index: 3422543 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0234. Min Range: -5.0234
Max Act: 4.8671. Min Act: -0.1700
Data Index: 7670014 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19