Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2800 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0367. Min Range: -9.0367
Max Act: 9.0367. Min Act: -0.1700
Data Index: 515767 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0367. Min Range: -9.0367
Max Act: 9.0367. Min Act: -0.1700
Data Index: 3534288 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.9742. Min Act: -0.1700
Data Index: 8117269 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.9117. Min Act: -0.1700
Data Index: 1223764 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.9117. Min Act: -0.1700
Data Index: 5727169 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.7242. Min Act: -0.1700
Data Index: 3534270 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.7242. Min Act: -0.1700
Data Index: 4852813 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.6617. Min Act: -0.1700
Data Index: 5351286 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.6617. Min Act: -0.1700
Data Index: 3125700 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.6617. Min Act: -0.1700
Data Index: 3534284 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.5992. Min Act: -0.1700
Data Index: 724373 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.5992. Min Act: -0.1700
Data Index: 2542925 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.5992. Min Act: -0.1700
Data Index: 3583368 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.5992. Min Act: -0.1700
Data Index: 3514768 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.5367. Min Act: -0.1700
Data Index: 597591 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.5367. Min Act: -0.1700
Data Index: 7000545 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.4742. Min Act: -0.1700
Data Index: 6935719 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.4742. Min Act: -0.1700
Data Index: 6753229 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.4742. Min Act: -0.1700
Data Index: 4342316 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0367. Min Range: -9.0367
Max Act: 8.4742. Min Act: -0.1700
Data Index: 1185677 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19