Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.6334. Min Act: -0.1700
Data Index: 6315815 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.6022. Min Act: -0.1700
Data Index: 6031283 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.6022. Min Act: -0.1700
Data Index: 3835625 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.5709. Min Act: -0.1700
Data Index: 4602468 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.5397. Min Act: -0.1700
Data Index: 2328496 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.5397. Min Act: -0.1700
Data Index: 920979 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.5397. Min Act: -0.1700
Data Index: 1497971 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.5084. Min Act: -0.1700
Data Index: 3729230 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.4772. Min Act: -0.1700
Data Index: 3246793 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.4772. Min Act: -0.1700
Data Index: 184406 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.4772. Min Act: -0.1700
Data Index: 4119290 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.4772. Min Act: -0.1700
Data Index: 1623879 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.4147. Min Act: -0.1700
Data Index: 6642468 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.4147. Min Act: -0.1700
Data Index: 7649128 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.3834. Min Act: -0.1700
Data Index: 2106479 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.3834. Min Act: -0.1700
Data Index: 2346243 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.4147. Min Act: -0.1700
Data Index: 5668751 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.4147. Min Act: -0.1700
Data Index: 6430523 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.3834. Min Act: -0.1700
Data Index: 8221001 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6334. Min Range: -5.6334
Max Act: 5.3522. Min Act: -0.1700
Data Index: 237494 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19