Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5905 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0226. Min Range: -7.0226
Max Act: 7.0226. Min Act: -0.1700
Data Index: 1699901 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.6476. Min Act: -0.1700
Data Index: 4112787 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.5538. Min Act: -0.1700
Data Index: 6950279 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.5538. Min Act: -0.1700
Data Index: 4119533 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.4601. Min Act: -0.1700
Data Index: 7464897 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.4288. Min Act: -0.1700
Data Index: 989854 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3663. Min Act: -0.1700
Data Index: 3042542 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3976. Min Act: -0.1700
Data Index: 6167591 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3976. Min Act: -0.1700
Data Index: 1193393 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3976. Min Act: -0.1700
Data Index: 159998 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3663. Min Act: -0.1700
Data Index: 6985426 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3976. Min Act: -0.1700
Data Index: 7033265 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3663. Min Act: -0.1700
Data Index: 1240794 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3351. Min Act: -0.1700
Data Index: 2344257 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3351. Min Act: -0.1700
Data Index: 7318379 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3351. Min Act: -0.1700
Data Index: 3964856 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3351. Min Act: -0.1700
Data Index: 4046975 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3038. Min Act: -0.1700
Data Index: 2166727 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.2726. Min Act: -0.1700
Data Index: 1117714 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0226. Min Range: -7.0226
Max Act: 6.3038. Min Act: -0.1700
Data Index: 3811426 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19