Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.3473. Min Act: -0.1700
Data Index: 4010295 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.3161. Min Act: -0.1700
Data Index: 894277 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.2223. Min Act: -0.1700
Data Index: 8820577 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.2223. Min Act: -0.1700
Data Index: 4129969 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.1911. Min Act: -0.1700
Data Index: 4527754 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.1286. Min Act: -0.1700
Data Index: 2240977 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.1286. Min Act: -0.1700
Data Index: 3252329 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.0973. Min Act: -0.1700
Data Index: 1251547 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.0973. Min Act: -0.1700
Data Index: 8129211 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.0661. Min Act: -0.1700
Data Index: 942284 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.0661. Min Act: -0.1700
Data Index: 4124428 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.0036. Min Act: -0.1700
Data Index: 248521 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.0036. Min Act: -0.1700
Data Index: 2255903 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3473. Min Range: -7.3473
Max Act: 7.0036. Min Act: -0.1700
Data Index: 4933417 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3473. Min Range: -7.3473
Max Act: 6.9723. Min Act: -0.1700
Data Index: 8390325 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3473. Min Range: -7.3473
Max Act: 6.9723. Min Act: -0.1700
Data Index: 6656296 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3473. Min Range: -7.3473
Max Act: 6.9723. Min Act: -0.1700
Data Index: 6753380 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3473. Min Range: -7.3473
Max Act: 6.9411. Min Act: -0.1700
Data Index: 1534415 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3473. Min Range: -7.3473
Max Act: 6.9411. Min Act: -0.1700
Data Index: 7394413 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3473. Min Range: -7.3473
Max Act: 6.9411. Min Act: -0.1700
Data Index: 6306393 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19