Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1490. Min Range: -4.1490
Max Act: 4.1490. Min Act: -0.1700
Data Index: 1953322 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1490. Min Range: -4.1490
Max Act: 4.0865. Min Act: -0.1700
Data Index: 6517982 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1490. Min Range: -4.1490
Max Act: 4.0865. Min Act: -0.1700
Data Index: 3778555 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1490. Min Range: -4.1490
Max Act: 4.0865. Min Act: -0.1700
Data Index: 4816800 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1490. Min Range: -4.1490
Max Act: 4.0552. Min Act: -0.1700
Data Index: 5508139 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1490. Min Range: -4.1490
Max Act: 4.0552. Min Act: -0.1700
Data Index: 2751255 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1490. Min Range: -4.1490
Max Act: 4.0239. Min Act: -0.1700
Data Index: 4527140 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1490. Min Range: -4.1490
Max Act: 4.0239. Min Act: -0.1700
Data Index: 8691437 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1490. Min Range: -4.1490
Max Act: 4.0239. Min Act: -0.1700
Data Index: 5751148 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1490. Min Range: -4.1490
Max Act: 3.9614. Min Act: -0.1700
Data Index: 5776688 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1490. Min Range: -4.1490
Max Act: 3.9927. Min Act: -0.1700
Data Index: 5279775 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1490. Min Range: -4.1490
Max Act: 3.9614. Min Act: -0.1700
Data Index: 7230219 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1490. Min Range: -4.1490
Max Act: 3.9614. Min Act: -0.1700
Data Index: 299154 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1490. Min Range: -4.1490
Max Act: 3.9614. Min Act: -0.1700
Data Index: 3799968 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1490. Min Range: -4.1490
Max Act: 3.9927. Min Act: -0.1700
Data Index: 3963141 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1490. Min Range: -4.1490
Max Act: 3.9302. Min Act: -0.1700
Data Index: 1956795 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1490. Min Range: -4.1490
Max Act: 3.9302. Min Act: -0.1700
Data Index: 4469721 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1490. Min Range: -4.1490
Max Act: 3.9302. Min Act: -0.1700
Data Index: 4946407 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1490. Min Range: -4.1490
Max Act: 3.9302. Min Act: -0.1700
Data Index: 1736698 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1490. Min Range: -4.1490
Max Act: 3.8989. Min Act: -0.1700
Data Index: 3088703 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19