Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 24 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.7320. Min Act: -0.1700
Data Index: 8173724 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.6068. Min Act: -0.1700
Data Index: 7181084 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.2463. Min Act: -0.1700
Data Index: 8455631 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.2149. Min Act: -0.1700
Data Index: 872270 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.2149. Min Act: -0.1700
Data Index: 1115231 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.2149. Min Act: -0.1700
Data Index: 2722796 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1677. Min Act: -0.1700
Data Index: 7363434 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1991. Min Act: -0.1700
Data Index: 4170543 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1991. Min Act: -0.1700
Data Index: 5322319 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1677. Min Act: -0.1700
Data Index: 1157097 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1834. Min Act: -0.1700
Data Index: 2395543 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1677. Min Act: -0.1700
Data Index: 6139893 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1519. Min Act: -0.1700
Data Index: 8806088 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1519. Min Act: -0.1700
Data Index: 1068938 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1519. Min Act: -0.1700
Data Index: 6289358 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1677. Min Act: -0.1700
Data Index: 3068549 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1519. Min Act: -0.1700
Data Index: 578760 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1519. Min Act: -0.1700
Data Index: 4664812 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1204. Min Act: -0.1700
Data Index: 4704333 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7320. Min Range: -3.7320
Max Act: 3.1204. Min Act: -0.1700
Data Index: 8113275 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19