Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 673 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2441. Min Range: -8.2441
Max Act: 8.2441. Min Act: -0.1700
Data Index: 5628169 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2441. Min Range: -8.2441
Max Act: 8.1191. Min Act: -0.1700
Data Index: 6458659 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.9941. Min Act: -0.1700
Data Index: 2023188 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.9004. Min Act: -0.1700
Data Index: 8672882 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.8066. Min Act: -0.1700
Data Index: 4041092 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.6816. Min Act: -0.1700
Data Index: 6022777 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.5879. Min Act: -0.1700
Data Index: 17924 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.5879. Min Act: -0.1700
Data Index: 423650 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.5566. Min Act: -0.1700
Data Index: 7105970 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.5254. Min Act: -0.1700
Data Index: 8068646 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.5254. Min Act: -0.1700
Data Index: 6666516 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.4941. Min Act: -0.1700
Data Index: 3553752 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.4941. Min Act: -0.1700
Data Index: 727285 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.4941. Min Act: -0.1700
Data Index: 400788 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.4941. Min Act: -0.1700
Data Index: 6106304 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.4941. Min Act: -0.1700
Data Index: 6935409 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.4629. Min Act: -0.1700
Data Index: 6395049 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.4629. Min Act: -0.1700
Data Index: 3168486 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.4629. Min Act: -0.1700
Data Index: 8773967 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2441. Min Range: -8.2441
Max Act: 7.4004. Min Act: -0.1700
Data Index: 4928148 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19