Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3167 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2319. Min Range: -5.2319
Max Act: 5.2319. Min Act: -0.1700
Data Index: 6300786 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2319. Min Range: -5.2319
Max Act: 5.1382. Min Act: -0.1700
Data Index: 8429255 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2319. Min Range: -5.2319
Max Act: 5.0757. Min Act: -0.1700
Data Index: 6173135 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2319. Min Range: -5.2319
Max Act: 5.0757. Min Act: -0.1700
Data Index: 8551578 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2319. Min Range: -5.2319
Max Act: 5.0444. Min Act: -0.1700
Data Index: 991226 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2319. Min Range: -5.2319
Max Act: 5.0444. Min Act: -0.1700
Data Index: 4347077 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2319. Min Range: -5.2319
Max Act: 5.0132. Min Act: -0.1700
Data Index: 8224672 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2319. Min Range: -5.2319
Max Act: 5.0132. Min Act: -0.1700
Data Index: 6960799 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2319. Min Range: -5.2319
Max Act: 4.9507. Min Act: -0.1700
Data Index: 1368304 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2319. Min Range: -5.2319
Max Act: 4.9819. Min Act: -0.1700
Data Index: 5697523 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2319. Min Range: -5.2319
Max Act: 5.0132. Min Act: -0.1700
Data Index: 5641395 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2319. Min Range: -5.2319
Max Act: 4.9507. Min Act: -0.1700
Data Index: 6986871 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2319. Min Range: -5.2319
Max Act: 4.9507. Min Act: -0.1700
Data Index: 7066621 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2319. Min Range: -5.2319
Max Act: 4.9194. Min Act: -0.1700
Data Index: 4202227 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2319. Min Range: -5.2319
Max Act: 4.9507. Min Act: -0.1700
Data Index: 2849549 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2319. Min Range: -5.2319
Max Act: 4.9194. Min Act: -0.1700
Data Index: 1795714 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2319. Min Range: -5.2319
Max Act: 4.9507. Min Act: -0.1700
Data Index: 3293507 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2319. Min Range: -5.2319
Max Act: 4.9507. Min Act: -0.1700
Data Index: 7674408 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2319. Min Range: -5.2319
Max Act: 4.9194. Min Act: -0.1700
Data Index: 1843473 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2319. Min Range: -5.2319
Max Act: 4.9507. Min Act: -0.1700
Data Index: 8056990 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19