Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1814 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.4236. Min Act: -0.1700
Data Index: 6808419 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.3611. Min Act: -0.1700
Data Index: 3100929 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.2674. Min Act: -0.1700
Data Index: 8553322 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.2361. Min Act: -0.1700
Data Index: 3431966 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.1736. Min Act: -0.1700
Data Index: 1499098 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.2049. Min Act: -0.1700
Data Index: 2486432 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.1111. Min Act: -0.1700
Data Index: 8807105 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0486. Min Act: -0.1700
Data Index: 6246271 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0799. Min Act: -0.1700
Data Index: 5476809 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0799. Min Act: -0.1700
Data Index: 3797924 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0174. Min Act: -0.1700
Data Index: 4934456 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0486. Min Act: -0.1700
Data Index: 8106779 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0486. Min Act: -0.1700
Data Index: 1582746 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0174. Min Act: -0.1700
Data Index: 1350963 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4236. Min Range: -5.4236
Max Act: 4.9861. Min Act: -0.1700
Data Index: 7003427 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0174. Min Act: -0.1700
Data Index: 4876747 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0174. Min Act: -0.1700
Data Index: 1924871 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4236. Min Range: -5.4236
Max Act: 4.9861. Min Act: -0.1700
Data Index: 1029706 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4236. Min Range: -5.4236
Max Act: 4.9549. Min Act: -0.1700
Data Index: 6408108 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4236. Min Range: -5.4236
Max Act: 4.9861. Min Act: -0.1700
Data Index: 2000093 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19