Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.9149. Min Act: -0.1700
Data Index: 786727 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.6334. Min Act: -0.1700
Data Index: 1348082 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.6178. Min Act: -0.1700
Data Index: 5257492 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.6178. Min Act: -0.1700
Data Index: 3638445 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.6178. Min Act: -0.1700
Data Index: 3657659 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.6021. Min Act: -0.1700
Data Index: 6100048 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5865. Min Act: -0.1700
Data Index: 3089396 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5708. Min Act: -0.1700
Data Index: 4628250 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5708. Min Act: -0.1700
Data Index: 2826693 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5708. Min Act: -0.1700
Data Index: 8620883 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5552. Min Act: -0.1700
Data Index: 2057357 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5708. Min Act: -0.1700
Data Index: 3907733 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5395. Min Act: -0.1700
Data Index: 8763482 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5239. Min Act: -0.1700
Data Index: 6444869 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5552. Min Act: -0.1700
Data Index: 6204624 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5395. Min Act: -0.1700
Data Index: 8420763 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5395. Min Act: -0.1700
Data Index: 6952420 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5239. Min Act: -0.1700
Data Index: 1412580 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5082. Min Act: -0.1700
Data Index: 2010019 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9149. Min Range: -3.9149
Max Act: 3.5082. Min Act: -0.1700
Data Index: 306644 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19