Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3860 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.5841. Min Act: -0.1700
Data Index: 64455 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.5841. Min Act: -0.1700
Data Index: 6900769 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.5529. Min Act: -0.1700
Data Index: 6530414 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.4904. Min Act: -0.1700
Data Index: 3273362 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.4591. Min Act: -0.1700
Data Index: 7574627 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.4904. Min Act: -0.1700
Data Index: 6687471 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.4591. Min Act: -0.1700
Data Index: 7379471 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.4591. Min Act: -0.1700
Data Index: 5518390 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.4591. Min Act: -0.1700
Data Index: 7921687 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.4279. Min Act: -0.1700
Data Index: 3176711 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.3966. Min Act: -0.1700
Data Index: 889334 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.3654. Min Act: -0.1700
Data Index: 6177728 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.3966. Min Act: -0.1700
Data Index: 4207942 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.3966. Min Act: -0.1700
Data Index: 3912646 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.3966. Min Act: -0.1700
Data Index: 6773634 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.3654. Min Act: -0.1700
Data Index: 3853836 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.4279. Min Act: -0.1700
Data Index: 3489674 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.3966. Min Act: -0.1700
Data Index: 1249327 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.3966. Min Act: -0.1700
Data Index: 6875044 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5841. Min Range: -4.5841
Max Act: 4.3966. Min Act: -0.1700
Data Index: 3803297 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19