Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2697. Min Range: -6.2697
Max Act: 6.2697. Min Act: -0.1700
Data Index: 4112669 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2697. Min Range: -6.2697
Max Act: 6.2072. Min Act: -0.1700
Data Index: 4925855 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2697. Min Range: -6.2697
Max Act: 6.1760. Min Act: -0.1700
Data Index: 7574864 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2697. Min Range: -6.2697
Max Act: 6.1447. Min Act: -0.1700
Data Index: 5786394 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2697. Min Range: -6.2697
Max Act: 6.0510. Min Act: -0.1700
Data Index: 2909653 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2697. Min Range: -6.2697
Max Act: 6.0510. Min Act: -0.1700
Data Index: 3511571 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2697. Min Range: -6.2697
Max Act: 6.0510. Min Act: -0.1700
Data Index: 3080255 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.9885. Min Act: -0.1700
Data Index: 98443 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.9572. Min Act: -0.1700
Data Index: 4534958 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.9572. Min Act: -0.1700
Data Index: 81252 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.9260. Min Act: -0.1700
Data Index: 953396 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.8635. Min Act: -0.1700
Data Index: 1692859 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.8947. Min Act: -0.1700
Data Index: 4017832 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.8635. Min Act: -0.1700
Data Index: 7795238 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.8322. Min Act: -0.1700
Data Index: 5844397 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.7385. Min Act: -0.1700
Data Index: 6808487 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.7385. Min Act: -0.1700
Data Index: 4412998 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.7385. Min Act: -0.1700
Data Index: 2039131 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.7072. Min Act: -0.1700
Data Index: 3502127 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2697. Min Range: -6.2697
Max Act: 5.7385. Min Act: -0.1700
Data Index: 7365900 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19