Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 808 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.7743. Min Act: -0.1700
Data Index: 1041551 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.7118. Min Act: -0.1700
Data Index: 8722240 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.7118. Min Act: -0.1700
Data Index: 3346258 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.6806. Min Act: -0.1700
Data Index: 2014903 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.5556. Min Act: -0.1700
Data Index: 5601999 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.5556. Min Act: -0.1700
Data Index: 4520448 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.5868. Min Act: -0.1700
Data Index: 7904958 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.5868. Min Act: -0.1700
Data Index: 4496185 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.5556. Min Act: -0.1700
Data Index: 3939729 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.5243. Min Act: -0.1700
Data Index: 1778924 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.5243. Min Act: -0.1700
Data Index: 6915703 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.5243. Min Act: -0.1700
Data Index: 3495625 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.4931. Min Act: -0.1700
Data Index: 6190030 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.5243. Min Act: -0.1700
Data Index: 6130853 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.4618. Min Act: -0.1700
Data Index: 6620962 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.4931. Min Act: -0.1700
Data Index: 4030992 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.4618. Min Act: -0.1700
Data Index: 5142748 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.4618. Min Act: -0.1700
Data Index: 6864536 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.4931. Min Act: -0.1700
Data Index: 1059717 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7743. Min Range: -4.7743
Max Act: 4.4618. Min Act: -0.1700
Data Index: 1372907 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19