Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.5386. Min Act: -0.1700
Data Index: 7667388 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.3192. Min Act: -0.1700
Data Index: 1296168 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.3035. Min Act: -0.1700
Data Index: 7568896 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.2092. Min Act: -0.1700
Data Index: 479950 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.2092. Min Act: -0.1700
Data Index: 4586266 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.2092. Min Act: -0.1700
Data Index: 4757549 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.1620. Min Act: -0.1700
Data Index: 6490976 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.1777. Min Act: -0.1700
Data Index: 3758275 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.1463. Min Act: -0.1700
Data Index: 3793776 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.1305. Min Act: -0.1700
Data Index: 4028672 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.1148. Min Act: -0.1700
Data Index: 5608887 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.1305. Min Act: -0.1700
Data Index: 663758 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.1305. Min Act: -0.1700
Data Index: 3733496 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.1148. Min Act: -0.1700
Data Index: 3432617 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.1148. Min Act: -0.1700
Data Index: 2584896 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.0990. Min Act: -0.1700
Data Index: 8318268 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.0832. Min Act: -0.1700
Data Index: 7716166 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.0832. Min Act: -0.1700
Data Index: 2372486 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.0832. Min Act: -0.1700
Data Index: 3427054 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5386. Min Range: -3.5386
Max Act: 3.0675. Min Act: -0.1700
Data Index: 3114031 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19