Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2094 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0382. Min Range: -8.0382
Max Act: 8.0382. Min Act: -0.1700
Data Index: 329790 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0382. Min Range: -8.0382
Max Act: 8.0069. Min Act: -0.1700
Data Index: 3067402 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.9757. Min Act: -0.1700
Data Index: 2057464 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.8194. Min Act: -0.1700
Data Index: 8620245 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.8507. Min Act: -0.1700
Data Index: 6333266 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.8194. Min Act: -0.1700
Data Index: 6674844 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.6944. Min Act: -0.1700
Data Index: 5842407 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.6632. Min Act: -0.1700
Data Index: 8372114 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.6319. Min Act: -0.1700
Data Index: 5289982 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.5382. Min Act: -0.1700
Data Index: 5924081 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.5382. Min Act: -0.1700
Data Index: 1425259 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.4757. Min Act: -0.1700
Data Index: 6674843 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.4757. Min Act: -0.1700
Data Index: 1360987 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.4444. Min Act: -0.1700
Data Index: 6627956 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.3507. Min Act: -0.1700
Data Index: 6012356 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.3819. Min Act: -0.1700
Data Index: 4638691 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.3819. Min Act: -0.1700
Data Index: 6936479 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.2882. Min Act: -0.1700
Data Index: 2205413 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.2882. Min Act: -0.1700
Data Index: 1273374 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0382. Min Range: -8.0382
Max Act: 7.2257. Min Act: -0.1700
Data Index: 3086055 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19