Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1482 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.7339. Min Act: -0.1700
Data Index: 8828144 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.7339. Min Act: -0.1700
Data Index: 7378635 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.7027. Min Act: -0.1700
Data Index: 3053348 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.7339. Min Act: -0.1700
Data Index: 2445685 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.5464. Min Act: -0.1700
Data Index: 2984826 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.4839. Min Act: -0.1700
Data Index: 4464931 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.4214. Min Act: -0.1700
Data Index: 3526633 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.3589. Min Act: -0.1700
Data Index: 598796 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.3277. Min Act: -0.1700
Data Index: 1609891 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.2964. Min Act: -0.1700
Data Index: 3257929 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.2339. Min Act: -0.1700
Data Index: 1641397 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.2339. Min Act: -0.1700
Data Index: 2778376 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.2339. Min Act: -0.1700
Data Index: 1091985 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.2339. Min Act: -0.1700
Data Index: 105091 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.2339. Min Act: -0.1700
Data Index: 7883860 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.2027. Min Act: -0.1700
Data Index: 735425 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.1714. Min Act: -0.1700
Data Index: 1309534 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.1714. Min Act: -0.1700
Data Index: 5429071 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.1402. Min Act: -0.1700
Data Index: 3364330 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7339. Min Range: -6.7339
Max Act: 6.1402. Min Act: -0.1700
Data Index: 7844750 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19