Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.8817. Min Act: -0.1700
Data Index: 7576585 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.8817. Min Act: -0.1700
Data Index: 8825196 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.8504. Min Act: -0.1700
Data Index: 3519840 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.8191. Min Act: -0.1700
Data Index: 2548954 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.8191. Min Act: -0.1700
Data Index: 2024316 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.8191. Min Act: -0.1700
Data Index: 1445593 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.8191. Min Act: -0.1700
Data Index: 7830327 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.7879. Min Act: -0.1700
Data Index: 7649477 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.8191. Min Act: -0.1700
Data Index: 6183461 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.7879. Min Act: -0.1700
Data Index: 5689624 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.7879. Min Act: -0.1700
Data Index: 5100170 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.7879. Min Act: -0.1700
Data Index: 4449575 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.7879. Min Act: -0.1700
Data Index: 7557528 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.7879. Min Act: -0.1700
Data Index: 2761379 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.8191. Min Act: -0.1700
Data Index: 1345665 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.7566. Min Act: -0.1700
Data Index: 442262 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.7879. Min Act: -0.1700
Data Index: 7290767 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.7879. Min Act: -0.1700
Data Index: 441442 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.7566. Min Act: -0.1700
Data Index: 5521471 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8817. Min Range: -3.8817
Max Act: 3.7253. Min Act: -0.1700
Data Index: 5844072 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19