Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4891 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.9265. Min Act: -0.1700
Data Index: 1143833 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.8313. Min Act: -0.1700
Data Index: 1059123 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.7835. Min Act: -0.1700
Data Index: 4205123 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.7676. Min Act: -0.1700
Data Index: 740213 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.6716. Min Act: -0.1700
Data Index: 3706395 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.6877. Min Act: -0.1700
Data Index: 6803588 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.6396. Min Act: -0.1700
Data Index: 6371329 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.6396. Min Act: -0.1700
Data Index: 8092490 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.6235. Min Act: -0.1700
Data Index: 6367584 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.5913. Min Act: -0.1700
Data Index: 21683 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.5752. Min Act: -0.1700
Data Index: 7541862 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.5913. Min Act: -0.1700
Data Index: 2454520 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.5591. Min Act: -0.1700
Data Index: 6688217 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.5268. Min Act: -0.1700
Data Index: 1665175 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.5429. Min Act: -0.1700
Data Index: 1531653 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.5268. Min Act: -0.1700
Data Index: 8075874 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.5268. Min Act: -0.1700
Data Index: 475860 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.5268. Min Act: -0.1700
Data Index: 3407709 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.5268. Min Act: -0.1700
Data Index: 3632624 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9265. Min Range: -2.9265
Max Act: 2.5268. Min Act: -0.1700
Data Index: 1130027 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19