Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5193 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3477. Min Range: -11.3477
Max Act: 11.3477. Min Act: -0.1700
Data Index: 2610743 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3477. Min Range: -11.3477
Max Act: 11.0352. Min Act: -0.1700
Data Index: 4152116 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.9102. Min Act: -0.1700
Data Index: 2662508 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.8477. Min Act: -0.1700
Data Index: 6093772 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.7227. Min Act: -0.1700
Data Index: 4253405 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.7852. Min Act: -0.1700
Data Index: 346880 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.7227. Min Act: -0.1700
Data Index: 4642301 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.7227. Min Act: -0.1700
Data Index: 5940034 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.7227. Min Act: -0.1700
Data Index: 2501100 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.6602. Min Act: -0.1700
Data Index: 3269579 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.5977. Min Act: -0.1700
Data Index: 4467202 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.5977. Min Act: -0.1700
Data Index: 6330103 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.5352. Min Act: -0.1700
Data Index: 3392401 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.5977. Min Act: -0.1700
Data Index: 4201659 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.5352. Min Act: -0.1700
Data Index: 5853162 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.4102. Min Act: -0.1700
Data Index: 2764593 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.4727. Min Act: -0.1700
Data Index: 364394 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.4102. Min Act: -0.1700
Data Index: 4083797 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.4102. Min Act: -0.1700
Data Index: 2036353 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3477. Min Range: -11.3477
Max Act: 10.4102. Min Act: -0.1700
Data Index: 1744508 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19