Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2969 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.3912. Min Act: -0.1700
Data Index: 4011307 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.2350. Min Act: -0.1700
Data Index: 7696985 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.2037. Min Act: -0.1700
Data Index: 3493220 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.1725. Min Act: -0.1700
Data Index: 3780531 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.1100. Min Act: -0.1700
Data Index: 2649559 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.1100. Min Act: -0.1700
Data Index: 3200010 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.1100. Min Act: -0.1700
Data Index: 8201781 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.1100. Min Act: -0.1700
Data Index: 371564 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.0787. Min Act: -0.1700
Data Index: 4516189 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.0475. Min Act: -0.1700
Data Index: 1436424 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.0475. Min Act: -0.1700
Data Index: 2473971 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.9850. Min Act: -0.1700
Data Index: 806137 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.9850. Min Act: -0.1700
Data Index: 3754884 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.9850. Min Act: -0.1700
Data Index: 453973 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.9537. Min Act: -0.1700
Data Index: 5583975 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.9537. Min Act: -0.1700
Data Index: 1028693 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.9537. Min Act: -0.1700
Data Index: 2119054 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.9225. Min Act: -0.1700
Data Index: 7783604 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.8912. Min Act: -0.1700
Data Index: 2314235 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.8912. Min Act: -0.1700
Data Index: 5183753 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19