Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5472. Min Range: -5.5472
Max Act: 5.5472. Min Act: -0.1700
Data Index: 1379213 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5472. Min Range: -5.5472
Max Act: 5.4534. Min Act: -0.1700
Data Index: 7020901 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5472. Min Range: -5.5472
Max Act: 5.3597. Min Act: -0.1700
Data Index: 3622542 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5472. Min Range: -5.5472
Max Act: 5.1409. Min Act: -0.1700
Data Index: 1139011 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5472. Min Range: -5.5472
Max Act: 5.1409. Min Act: -0.1700
Data Index: 4751111 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5472. Min Range: -5.5472
Max Act: 5.0472. Min Act: -0.1700
Data Index: 109217 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.9847. Min Act: -0.1700
Data Index: 2722474 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.9847. Min Act: -0.1700
Data Index: 532709 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.9534. Min Act: -0.1700
Data Index: 5691924 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.9222. Min Act: -0.1700
Data Index: 637202 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.9534. Min Act: -0.1700
Data Index: 8781340 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.9534. Min Act: -0.1700
Data Index: 8743311 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.9534. Min Act: -0.1700
Data Index: 2587271 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.9222. Min Act: -0.1700
Data Index: 8515388 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.9222. Min Act: -0.1700
Data Index: 6270639 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.8909. Min Act: -0.1700
Data Index: 7619704 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.8909. Min Act: -0.1700
Data Index: 5863170 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.8909. Min Act: -0.1700
Data Index: 2724744 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.8909. Min Act: -0.1700
Data Index: 2590702 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5472. Min Range: -5.5472
Max Act: 4.8597. Min Act: -0.1700
Data Index: 4813959 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19