Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 411 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.4221. Min Act: -0.1700
Data Index: 2673258 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.3909. Min Act: -0.1700
Data Index: 3057744 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.4221. Min Act: -0.1700
Data Index: 1603662 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.3284. Min Act: -0.1700
Data Index: 2624024 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.3284. Min Act: -0.1700
Data Index: 1992673 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.3284. Min Act: -0.1700
Data Index: 5564046 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.2346. Min Act: -0.1700
Data Index: 502083 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.2034. Min Act: -0.1700
Data Index: 8038862 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.2034. Min Act: -0.1700
Data Index: 3188388 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.2034. Min Act: -0.1700
Data Index: 3689283 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.1409. Min Act: -0.1700
Data Index: 6763116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.1409. Min Act: -0.1700
Data Index: 6518654 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.1409. Min Act: -0.1700
Data Index: 2990608 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.1409. Min Act: -0.1700
Data Index: 5860019 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.1096. Min Act: -0.1700
Data Index: 8403782 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.1096. Min Act: -0.1700
Data Index: 1840730 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.1096. Min Act: -0.1700
Data Index: 8672752 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.0784. Min Act: -0.1700
Data Index: 4012882 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.1096. Min Act: -0.1700
Data Index: 8369491 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4221. Min Range: -7.4221
Max Act: 7.0784. Min Act: -0.1700
Data Index: 6865459 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19