Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 390 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1397. Min Range: -7.1397
Max Act: 7.1397. Min Act: -0.1700
Data Index: 2132365 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.8584. Min Act: -0.1700
Data Index: 7094839 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.8272. Min Act: -0.1700
Data Index: 1120047 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.7647. Min Act: -0.1700
Data Index: 1817950 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.7022. Min Act: -0.1700
Data Index: 391712 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.6397. Min Act: -0.1700
Data Index: 1993080 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.6084. Min Act: -0.1700
Data Index: 2524931 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.5147. Min Act: -0.1700
Data Index: 8254352 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.5147. Min Act: -0.1700
Data Index: 8385774 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.5147. Min Act: -0.1700
Data Index: 786683 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.4834. Min Act: -0.1700
Data Index: 8762318 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.4834. Min Act: -0.1700
Data Index: 2246595 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.3897. Min Act: -0.1700
Data Index: 2261047 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.3897. Min Act: -0.1700
Data Index: 2644481 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.3584. Min Act: -0.1700
Data Index: 1747549 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.2959. Min Act: -0.1700
Data Index: 147693 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.2959. Min Act: -0.1700
Data Index: 3852660 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.3272. Min Act: -0.1700
Data Index: 4831393 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.2647. Min Act: -0.1700
Data Index: 7606300 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1397. Min Range: -7.1397
Max Act: 6.2647. Min Act: -0.1700
Data Index: 4348666 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19