Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.9273. Min Act: -0.1700
Data Index: 1643560 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.9273. Min Act: -0.1700
Data Index: 6598465 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.6460. Min Act: -0.1700
Data Index: 3963576 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.6460. Min Act: -0.1700
Data Index: 3492673 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.5523. Min Act: -0.1700
Data Index: 6975723 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.5210. Min Act: -0.1700
Data Index: 585865 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.4898. Min Act: -0.1700
Data Index: 4372851 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.4898. Min Act: -0.1700
Data Index: 6862383 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.4585. Min Act: -0.1700
Data Index: 870389 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.4585. Min Act: -0.1700
Data Index: 2246663 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.4273. Min Act: -0.1700
Data Index: 7273825 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.3960. Min Act: -0.1700
Data Index: 2846 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.3960. Min Act: -0.1700
Data Index: 1891193 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.3960. Min Act: -0.1700
Data Index: 6930637 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.3960. Min Act: -0.1700
Data Index: 1679317 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.3648. Min Act: -0.1700
Data Index: 5349154 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.3648. Min Act: -0.1700
Data Index: 6936374 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.3335. Min Act: -0.1700
Data Index: 12218 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.3335. Min Act: -0.1700
Data Index: 2307381 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9273. Min Range: -4.9273
Max Act: 4.3335. Min Act: -0.1700
Data Index: 6755076 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19