Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3320. Min Range: -7.3320
Max Act: 7.3320. Min Act: -0.1700
Data Index: 519595 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3320. Min Range: -7.3320
Max Act: 7.2070. Min Act: -0.1700
Data Index: 6046262 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3320. Min Range: -7.3320
Max Act: 7.2070. Min Act: -0.1700
Data Index: 7500819 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3320. Min Range: -7.3320
Max Act: 7.1758. Min Act: -0.1700
Data Index: 7517383 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3320. Min Range: -7.3320
Max Act: 7.0820. Min Act: -0.1700
Data Index: 508683 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3320. Min Range: -7.3320
Max Act: 7.0820. Min Act: -0.1700
Data Index: 262143 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3320. Min Range: -7.3320
Max Act: 7.0508. Min Act: -0.1700
Data Index: 3058551 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3320. Min Range: -7.3320
Max Act: 7.0508. Min Act: -0.1700
Data Index: 4981140 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3320. Min Range: -7.3320
Max Act: 7.0195. Min Act: -0.1700
Data Index: 2681895 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3320. Min Range: -7.3320
Max Act: 7.0195. Min Act: -0.1700
Data Index: 4498112 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3320. Min Range: -7.3320
Max Act: 7.0195. Min Act: -0.1700
Data Index: 7305757 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3320. Min Range: -7.3320
Max Act: 7.0195. Min Act: -0.1700
Data Index: 5329800 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3320. Min Range: -7.3320
Max Act: 6.9883. Min Act: -0.1700
Data Index: 4814958 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3320. Min Range: -7.3320
Max Act: 6.9883. Min Act: -0.1700
Data Index: 6342797 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3320. Min Range: -7.3320
Max Act: 6.9883. Min Act: -0.1700
Data Index: 8317203 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3320. Min Range: -7.3320
Max Act: 6.9570. Min Act: -0.1700
Data Index: 265741 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3320. Min Range: -7.3320
Max Act: 6.9570. Min Act: -0.1700
Data Index: 4428795 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3320. Min Range: -7.3320
Max Act: 6.9258. Min Act: -0.1700
Data Index: 4612821 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3320. Min Range: -7.3320
Max Act: 6.9258. Min Act: -0.1700
Data Index: 613421 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3320. Min Range: -7.3320
Max Act: 6.9570. Min Act: -0.1700
Data Index: 470884 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19