Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4491 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.2665. Min Act: -0.1700
Data Index: 4323410 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.2978. Min Act: -0.1700
Data Index: 2866931 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.2352. Min Act: -0.1700
Data Index: 8298200 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.2040. Min Act: -0.1700
Data Index: 8421207 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.2040. Min Act: -0.1700
Data Index: 6543534 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.1727. Min Act: -0.1700
Data Index: 6096521 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.2040. Min Act: -0.1700
Data Index: 4763345 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.2040. Min Act: -0.1700
Data Index: 3804498 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.1727. Min Act: -0.1700
Data Index: 6307127 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.1727. Min Act: -0.1700
Data Index: 768859 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.1727. Min Act: -0.1700
Data Index: 7224715 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.1727. Min Act: -0.1700
Data Index: 8114449 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.1727. Min Act: -0.1700
Data Index: 7594038 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.1727. Min Act: -0.1700
Data Index: 847410 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.1727. Min Act: -0.1700
Data Index: 8302946 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.1415. Min Act: -0.1700
Data Index: 7594039 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.1102. Min Act: -0.1700
Data Index: 3121326 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.1102. Min Act: -0.1700
Data Index: 2401764 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.1102. Min Act: -0.1700
Data Index: 8550776 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2978. Min Range: -4.2978
Max Act: 4.0790. Min Act: -0.1700
Data Index: 4513289 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19