Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.9003. Min Act: -0.1700
Data Index: 898341 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.9003. Min Act: -0.1700
Data Index: 2025349 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.8378. Min Act: -0.1700
Data Index: 7502668 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.6815. Min Act: -0.1700
Data Index: 8717199 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.6190. Min Act: -0.1700
Data Index: 3304108 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.4940. Min Act: -0.1700
Data Index: 7079361 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.5253. Min Act: -0.1700
Data Index: 653412 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.4940. Min Act: -0.1700
Data Index: 1067743 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.4940. Min Act: -0.1700
Data Index: 412775 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.4940. Min Act: -0.1700
Data Index: 2959834 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.4628. Min Act: -0.1700
Data Index: 808179 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.4628. Min Act: -0.1700
Data Index: 1352123 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.4628. Min Act: -0.1700
Data Index: 7824926 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.4628. Min Act: -0.1700
Data Index: 6835122 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.4003. Min Act: -0.1700
Data Index: 4165802 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.3690. Min Act: -0.1700
Data Index: 6319832 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.3690. Min Act: -0.1700
Data Index: 865725 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.3690. Min Act: -0.1700
Data Index: 5238592 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.3378. Min Act: -0.1700
Data Index: 6424397 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9003. Min Range: -5.9003
Max Act: 5.3378. Min Act: -0.1700
Data Index: 6159554 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19