Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 42 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.5261. Min Act: -0.1700
Data Index: 3930220 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.4323. Min Act: -0.1700
Data Index: 7907361 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.3698. Min Act: -0.1700
Data Index: 532737 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.3698. Min Act: -0.1700
Data Index: 1245484 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.3386. Min Act: -0.1700
Data Index: 89932 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.2448. Min Act: -0.1700
Data Index: 1327867 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.2761. Min Act: -0.1700
Data Index: 922266 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.1823. Min Act: -0.1700
Data Index: 5470753 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.1823. Min Act: -0.1700
Data Index: 1507464 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.1511. Min Act: -0.1700
Data Index: 5182164 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.1198. Min Act: -0.1700
Data Index: 486873 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.1511. Min Act: -0.1700
Data Index: 7816500 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.1511. Min Act: -0.1700
Data Index: 824986 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.1198. Min Act: -0.1700
Data Index: 6386459 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.1198. Min Act: -0.1700
Data Index: 8723850 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.1198. Min Act: -0.1700
Data Index: 943555 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.0886. Min Act: -0.1700
Data Index: 5751140 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.1198. Min Act: -0.1700
Data Index: 903159 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.1198. Min Act: -0.1700
Data Index: 898398 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5261. Min Range: -5.5261
Max Act: 5.0886. Min Act: -0.1700
Data Index: 369516 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19