Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5860 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.4606. Min Act: -0.1700
Data Index: 8421187 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.2419. Min Act: -0.1700
Data Index: 2167184 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.2419. Min Act: -0.1700
Data Index: 8651613 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.2419. Min Act: -0.1700
Data Index: 1179904 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.2106. Min Act: -0.1700
Data Index: 1884674 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.2106. Min Act: -0.1700
Data Index: 7722523 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.1794. Min Act: -0.1700
Data Index: 6315284 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.1794. Min Act: -0.1700
Data Index: 7015291 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.1481. Min Act: -0.1699
Data Index: 3290553 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.1169. Min Act: -0.1700
Data Index: 8169301 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.1169. Min Act: -0.1700
Data Index: 1972378 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.0856. Min Act: -0.1700
Data Index: 876950 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.0856. Min Act: -0.1700
Data Index: 2534139 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.1169. Min Act: -0.1700
Data Index: 6957410 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.1169. Min Act: -0.1700
Data Index: 6395437 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.0856. Min Act: -0.1700
Data Index: 2696548 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.0856. Min Act: -0.1700
Data Index: 486289 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.0856. Min Act: -0.1700
Data Index: 1002385 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.0856. Min Act: -0.1700
Data Index: 6136396 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4606. Min Range: -5.4606
Max Act: 5.0856. Min Act: -0.1695
Data Index: 3670067 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19