Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3229 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.4549. Min Act: -0.1700
Data Index: 7721406 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.4236. Min Act: -0.1700
Data Index: 4177874 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.2049. Min Act: -0.1700
Data Index: 631399 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.2049. Min Act: -0.1700
Data Index: 4093307 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.1736. Min Act: -0.1700
Data Index: 5316708 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.1111. Min Act: -0.1700
Data Index: 5268140 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.1424. Min Act: -0.1700
Data Index: 1813965 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.1424. Min Act: -0.1700
Data Index: 3634631 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.1111. Min Act: -0.1700
Data Index: 1512685 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.0799. Min Act: -0.1700
Data Index: 5937552 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.0799. Min Act: -0.1700
Data Index: 7433432 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.1111. Min Act: -0.1700
Data Index: 3413381 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.0486. Min Act: -0.1700
Data Index: 354176 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.0486. Min Act: -0.1700
Data Index: 2217244 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.0174. Min Act: -0.1700
Data Index: 2150106 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.0174. Min Act: -0.1700
Data Index: 7077779 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.0174. Min Act: -0.1700
Data Index: 4413263 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4549. Min Range: -5.4549
Max Act: 5.0174. Min Act: -0.1700
Data Index: 7971766 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4549. Min Range: -5.4549
Max Act: 4.9861. Min Act: -0.1700
Data Index: 1687206 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4549. Min Range: -5.4549
Max Act: 4.9861. Min Act: -0.1700
Data Index: 5851386 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19