Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1155 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3966. Min Range: -8.3966
Max Act: 8.3966. Min Act: -0.1700
Data Index: 6726699 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3966. Min Range: -8.3966
Max Act: 8.2091. Min Act: -0.1700
Data Index: 1602416 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3966. Min Range: -8.3966
Max Act: 8.0216. Min Act: -0.1700
Data Index: 1339161 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.9591. Min Act: -0.1700
Data Index: 4738762 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.7716. Min Act: -0.1700
Data Index: 8497863 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.7716. Min Act: -0.1700
Data Index: 4247657 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.7091. Min Act: -0.1700
Data Index: 3670456 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.7091. Min Act: -0.1700
Data Index: 4496849 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.7091. Min Act: -0.1700
Data Index: 918017 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.7091. Min Act: -0.1700
Data Index: 6726126 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.6466. Min Act: -0.1700
Data Index: 2316994 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.5841. Min Act: -0.1700
Data Index: 7010591 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.6466. Min Act: -0.1700
Data Index: 4124435 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.5216. Min Act: -0.1700
Data Index: 5952130 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.5216. Min Act: -0.1700
Data Index: 1334104 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.4591. Min Act: -0.1700
Data Index: 6041051 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.4591. Min Act: -0.1700
Data Index: 1572051 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.4904. Min Act: -0.1700
Data Index: 240734 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.4279. Min Act: -0.1700
Data Index: 3772447 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3966. Min Range: -8.3966
Max Act: 7.3966. Min Act: -0.1700
Data Index: 1299023 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19