Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1428. Min Range: -5.1428
Max Act: 5.1428. Min Act: -0.1700
Data Index: 2381360 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1428. Min Range: -5.1428
Max Act: 5.0803. Min Act: -0.1700
Data Index: 1257383 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1428. Min Range: -5.1428
Max Act: 5.0491. Min Act: -0.1700
Data Index: 2014948 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1428. Min Range: -5.1428
Max Act: 5.0178. Min Act: -0.1700
Data Index: 1016072 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.9553. Min Act: -0.1700
Data Index: 4068377 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.9241. Min Act: -0.1700
Data Index: 410535 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.9241. Min Act: -0.1700
Data Index: 1102340 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.9241. Min Act: -0.1700
Data Index: 5935703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.8303. Min Act: -0.1700
Data Index: 5112908 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.8303. Min Act: -0.1700
Data Index: 4278463 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.8303. Min Act: -0.1700
Data Index: 6925884 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.8303. Min Act: -0.1700
Data Index: 3853012 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.7991. Min Act: -0.1700
Data Index: 2936824 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.7991. Min Act: -0.1700
Data Index: 246555 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.7678. Min Act: -0.1700
Data Index: 243392 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.7366. Min Act: -0.1700
Data Index: 7990387 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.7366. Min Act: -0.1700
Data Index: 4201105 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.7366. Min Act: -0.1700
Data Index: 1459488 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.7366. Min Act: -0.1700
Data Index: 6082486 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1428. Min Range: -5.1428
Max Act: 4.7366. Min Act: -0.1700
Data Index: 2556446 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19