Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1835 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.3553. Min Act: -0.1700
Data Index: 4580392 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.3240. Min Act: -0.1700
Data Index: 1875861 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.2928. Min Act: -0.1700
Data Index: 5209902 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.2928. Min Act: -0.1700
Data Index: 8235002 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.1990. Min Act: -0.1700
Data Index: 5634848 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.1678. Min Act: -0.1700
Data Index: 6189268 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.1990. Min Act: -0.1700
Data Index: 6178775 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.1678. Min Act: -0.1700
Data Index: 3260926 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.1678. Min Act: -0.1700
Data Index: 4195545 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.1678. Min Act: -0.1700
Data Index: 3377104 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.1678. Min Act: -0.1700
Data Index: 1908728 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.1365. Min Act: -0.1700
Data Index: 8372707 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.1365. Min Act: -0.1700
Data Index: 694912 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.1365. Min Act: -0.1700
Data Index: 4608300 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.1365. Min Act: -0.1700
Data Index: 1204836 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.1053. Min Act: -0.1700
Data Index: 5206105 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.0740. Min Act: -0.1700
Data Index: 3209997 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.0740. Min Act: -0.1700
Data Index: 8006556 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.0740. Min Act: -0.1700
Data Index: 4370282 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3553. Min Range: -5.3553
Max Act: 5.0740. Min Act: -0.1700
Data Index: 5833756 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19