Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4142 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.6356. Min Act: -0.1700
Data Index: 4798059 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.5419. Min Act: -0.1700
Data Index: 5315560 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.5106. Min Act: -0.1700
Data Index: 7604321 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.4169. Min Act: -0.1700
Data Index: 2683459 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3856. Min Act: -0.1700
Data Index: 5421868 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3544. Min Act: -0.1700
Data Index: 2161152 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3544. Min Act: -0.1700
Data Index: 5699261 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3544. Min Act: -0.1700
Data Index: 6552845 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3544. Min Act: -0.1700
Data Index: 5801275 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3231. Min Act: -0.1700
Data Index: 1035221 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.2919. Min Act: -0.1700
Data Index: 4563902 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.2606. Min Act: -0.1700
Data Index: 7991305 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.2606. Min Act: -0.1700
Data Index: 6103731 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.2606. Min Act: -0.1700
Data Index: 6318938 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.2919. Min Act: -0.1700
Data Index: 1413543 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.2294. Min Act: -0.1700
Data Index: 8753495 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.2294. Min Act: -0.1700
Data Index: 748384 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.2294. Min Act: -0.1700
Data Index: 7392120 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.1981. Min Act: -0.1700
Data Index: 260445 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.1669. Min Act: -0.1700
Data Index: 4338704 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19