Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1623 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.9534. Min Act: -0.1700
Data Index: 5038406 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.7659. Min Act: -0.1700
Data Index: 4360044 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.7346. Min Act: -0.1700
Data Index: 6261777 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.7034. Min Act: -0.1700
Data Index: 214426 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.6721. Min Act: -0.1700
Data Index: 1309681 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.6409. Min Act: -0.1700
Data Index: 4994332 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.6096. Min Act: -0.1700
Data Index: 8485511 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.6096. Min Act: -0.1700
Data Index: 8540066 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.5784. Min Act: -0.1700
Data Index: 2805090 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.5471. Min Act: -0.1700
Data Index: 437421 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.5471. Min Act: -0.1700
Data Index: 2584496 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.5159. Min Act: -0.1700
Data Index: 3610380 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.4846. Min Act: -0.1700
Data Index: 1699328 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.4846. Min Act: -0.1700
Data Index: 2314915 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.4846. Min Act: -0.1700
Data Index: 677026 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.4534. Min Act: -0.1700
Data Index: 7401678 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.4534. Min Act: -0.1700
Data Index: 6351934 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.4534. Min Act: -0.1700
Data Index: 2264052 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.4534. Min Act: -0.1700
Data Index: 2885383 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9534. Min Range: -5.9534
Max Act: 5.4221. Min Act: -0.1700
Data Index: 5599089 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19