Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 185 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1565. Min Range: -7.1565
Max Act: 7.1565. Min Act: -0.1700
Data Index: 4883661 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.9065. Min Act: -0.1700
Data Index: 8137381 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.8753. Min Act: -0.1700
Data Index: 7907918 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.7815. Min Act: -0.1700
Data Index: 3528045 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.7815. Min Act: -0.1700
Data Index: 2396680 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.7815. Min Act: -0.1700
Data Index: 1160726 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.7815. Min Act: -0.1700
Data Index: 8055146 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.7815. Min Act: -0.1700
Data Index: 6166283 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.6878. Min Act: -0.1700
Data Index: 4293116 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.6878. Min Act: -0.1700
Data Index: 384028 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.6565. Min Act: -0.1700
Data Index: 5764829 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.6565. Min Act: -0.1700
Data Index: 5770119 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.6253. Min Act: -0.1700
Data Index: 5922262 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.6253. Min Act: -0.1700
Data Index: 2687033 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.6253. Min Act: -0.1700
Data Index: 4274167 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.5940. Min Act: -0.1700
Data Index: 6920848 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.5628. Min Act: -0.1700
Data Index: 3591909 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.5628. Min Act: -0.1700
Data Index: 7677643 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.5628. Min Act: -0.1700
Data Index: 5483971 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1565. Min Range: -7.1565
Max Act: 6.5628. Min Act: -0.1700
Data Index: 4646793 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19