Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2527 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.7923. Min Act: -0.1700
Data Index: 2384484 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.6360. Min Act: -0.1700
Data Index: 1735099 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.4173. Min Act: -0.1700
Data Index: 7399871 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.3860. Min Act: -0.1700
Data Index: 3650423 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.3548. Min Act: -0.1700
Data Index: 4181479 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.3548. Min Act: -0.1700
Data Index: 8139263 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.3235. Min Act: -0.1700
Data Index: 1687288 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.3235. Min Act: -0.1700
Data Index: 3585735 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.2923. Min Act: -0.1700
Data Index: 1735101 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.2610. Min Act: -0.1700
Data Index: 5843176 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.2610. Min Act: -0.1700
Data Index: 497071 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.2298. Min Act: -0.1700
Data Index: 606126 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.2298. Min Act: -0.1700
Data Index: 2476253 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.2298. Min Act: -0.1700
Data Index: 6272922 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.1985. Min Act: -0.1700
Data Index: 6177873 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.1985. Min Act: -0.1700
Data Index: 3453428 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.1673. Min Act: -0.1700
Data Index: 4638758 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.1985. Min Act: -0.1700
Data Index: 166745 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.1985. Min Act: -0.1700
Data Index: 2158522 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7923. Min Range: -7.7923
Max Act: 7.1673. Min Act: -0.1700
Data Index: 2501976 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19