Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4713 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1243. Min Range: -7.1243
Max Act: 7.0931. Min Act: -0.1700
Data Index: 7631990 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1243. Min Range: -7.1243
Max Act: 7.1243. Min Act: -0.1700
Data Index: 6894821 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.8118. Min Act: -0.1700
Data Index: 3646934 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.6243. Min Act: -0.1700
Data Index: 3585690 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.5931. Min Act: -0.1700
Data Index: 7984400 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.5618. Min Act: -0.1700
Data Index: 4730902 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.5306. Min Act: -0.1700
Data Index: 5791212 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.4681. Min Act: -0.1700
Data Index: 7035287 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.4681. Min Act: -0.1700
Data Index: 489582 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.4368. Min Act: -0.1700
Data Index: 2674097 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.4056. Min Act: -0.1700
Data Index: 1138385 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.4056. Min Act: -0.1700
Data Index: 6827791 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.4056. Min Act: -0.1700
Data Index: 2767354 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.4368. Min Act: -0.1700
Data Index: 8499911 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.3743. Min Act: -0.1700
Data Index: 4915816 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.3743. Min Act: -0.1700
Data Index: 5223302 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.3743. Min Act: -0.1700
Data Index: 7615517 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.3743. Min Act: -0.1700
Data Index: 1126165 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.3118. Min Act: -0.1700
Data Index: 6634504 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1243. Min Range: -7.1243
Max Act: 6.2806. Min Act: -0.1700
Data Index: 6138057 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19