Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4002 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.7720. Min Act: -0.1700
Data Index: 2078929 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.7094. Min Act: -0.1700
Data Index: 1841688 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.6781. Min Act: -0.1700
Data Index: 4666052 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.6312. Min Act: -0.1700
Data Index: 1218757 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5999. Min Act: -0.1700
Data Index: 7203563 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5842. Min Act: -0.1700
Data Index: 8375268 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5999. Min Act: -0.1700
Data Index: 1146952 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5999. Min Act: -0.1700
Data Index: 1146945 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5842. Min Act: -0.1700
Data Index: 1912056 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5686. Min Act: -0.1700
Data Index: 4826964 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5999. Min Act: -0.1700
Data Index: 5890204 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5529. Min Act: -0.1700
Data Index: 748607 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5216. Min Act: -0.1700
Data Index: 7705575 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5216. Min Act: -0.1700
Data Index: 1841686 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4903. Min Act: -0.1700
Data Index: 4825365 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5060. Min Act: -0.1700
Data Index: 3836448 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4746. Min Act: -0.1700
Data Index: 2558686 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5060. Min Act: -0.1700
Data Index: 1841687 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4746. Min Act: -0.1700
Data Index: 5174816 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4590. Min Act: -0.1700
Data Index: 1500812 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19