Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1406 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.6286. Min Act: -0.1700
Data Index: 6292684 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.3786. Min Act: -0.1700
Data Index: 4369856 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.3786. Min Act: -0.1700
Data Index: 5980463 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.2848. Min Act: -0.1700
Data Index: 2386055 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.2848. Min Act: -0.1700
Data Index: 3475627 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.2536. Min Act: -0.1700
Data Index: 266031 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.2223. Min Act: -0.1700
Data Index: 4565911 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.1286. Min Act: -0.1700
Data Index: 3928538 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.0973. Min Act: -0.1700
Data Index: 259834 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.0661. Min Act: -0.1700
Data Index: 5719082 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.0036. Min Act: -0.1700
Data Index: 2471340 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.0661. Min Act: -0.1700
Data Index: 7130842 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.0036. Min Act: -0.1700
Data Index: 5341514 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6286. Min Range: -7.6286
Max Act: 6.9723. Min Act: -0.1700
Data Index: 6005420 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6286. Min Range: -7.6286
Max Act: 7.0036. Min Act: -0.1700
Data Index: 5371634 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6286. Min Range: -7.6286
Max Act: 6.9411. Min Act: -0.1700
Data Index: 4464761 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6286. Min Range: -7.6286
Max Act: 6.9411. Min Act: -0.1700
Data Index: 4157146 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6286. Min Range: -7.6286
Max Act: 6.9411. Min Act: -0.1700
Data Index: 1145302 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6286. Min Range: -7.6286
Max Act: 6.9411. Min Act: -0.1700
Data Index: 3940180 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6286. Min Range: -7.6286
Max Act: 6.9723. Min Act: -0.1700
Data Index: 454482 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19