Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0490. Min Range: -7.0490
Max Act: 7.0490. Min Act: -0.1700
Data Index: 7139425 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.9865. Min Act: -0.1700
Data Index: 1088528 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.8928. Min Act: -0.1700
Data Index: 3374470 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.8928. Min Act: -0.1700
Data Index: 7593958 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.8303. Min Act: -0.1700
Data Index: 1728914 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.6740. Min Act: -0.1700
Data Index: 5606156 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.6740. Min Act: -0.1700
Data Index: 3116619 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.6740. Min Act: -0.1700
Data Index: 4999018 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.6740. Min Act: -0.1700
Data Index: 7995671 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.6428. Min Act: -0.1700
Data Index: 5457382 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.5803. Min Act: -0.1700
Data Index: 2613365 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.5803. Min Act: -0.1700
Data Index: 5483594 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.5490. Min Act: -0.1700
Data Index: 1915214 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.5803. Min Act: -0.1700
Data Index: 8320829 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.5178. Min Act: -0.1700
Data Index: 6683696 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.5178. Min Act: -0.1700
Data Index: 2766673 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.4865. Min Act: -0.1700
Data Index: 2236341 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.4865. Min Act: -0.1700
Data Index: 4377824 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.4865. Min Act: -0.1700
Data Index: 4236760 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0490. Min Range: -7.0490
Max Act: 6.4553. Min Act: -0.1700
Data Index: 2900253 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19