Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2185 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.6275. Min Act: -0.1700
Data Index: 4051473 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.5962. Min Act: -0.1700
Data Index: 7765776 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.5650. Min Act: -0.1700
Data Index: 4997116 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.5650. Min Act: -0.1700
Data Index: 4436682 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.5025. Min Act: -0.1700
Data Index: 4179478 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.4712. Min Act: -0.1700
Data Index: 5775857 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.4400. Min Act: -0.1700
Data Index: 7774701 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.4087. Min Act: -0.1700
Data Index: 6174763 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.3150. Min Act: -0.1700
Data Index: 6416534 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.2212. Min Act: -0.1700
Data Index: 5944115 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.1900. Min Act: -0.1700
Data Index: 3261033 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.1587. Min Act: -0.1700
Data Index: 3543662 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.1900. Min Act: -0.1700
Data Index: 381516 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.1275. Min Act: -0.1700
Data Index: 8318471 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.1587. Min Act: -0.1700
Data Index: 863658 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.1275. Min Act: -0.1700
Data Index: 936055 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.1275. Min Act: -0.1700
Data Index: 7551219 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.0962. Min Act: -0.1700
Data Index: 8689690 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.0650. Min Act: -0.1700
Data Index: 5831079 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6275. Min Range: -7.6275
Max Act: 7.0962. Min Act: -0.1700
Data Index: 3360471 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19