Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5842 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8031. Min Range: -7.8031
Max Act: 7.8031. Min Act: -0.1700
Data Index: 6119284 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8031. Min Range: -7.8031
Max Act: 7.5219. Min Act: -0.1700
Data Index: 3338277 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8031. Min Range: -7.8031
Max Act: 7.4594. Min Act: -0.1700
Data Index: 5854550 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8031. Min Range: -7.8031
Max Act: 7.1781. Min Act: -0.1700
Data Index: 1772709 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8031. Min Range: -7.8031
Max Act: 7.1469. Min Act: -0.1700
Data Index: 7515988 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8031. Min Range: -7.8031
Max Act: 7.1469. Min Act: -0.1700
Data Index: 2960794 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8031. Min Range: -7.8031
Max Act: 7.1156. Min Act: -0.1700
Data Index: 7845838 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8031. Min Range: -7.8031
Max Act: 7.0844. Min Act: -0.1700
Data Index: 1876110 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8031. Min Range: -7.8031
Max Act: 7.0531. Min Act: -0.1700
Data Index: 4500166 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8031. Min Range: -7.8031
Max Act: 7.0219. Min Act: -0.1700
Data Index: 2703765 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8031. Min Range: -7.8031
Max Act: 6.9594. Min Act: -0.1700
Data Index: 8675729 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8031. Min Range: -7.8031
Max Act: 6.9594. Min Act: -0.1700
Data Index: 1471644 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8031. Min Range: -7.8031
Max Act: 6.9594. Min Act: -0.1700
Data Index: 4063972 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8031. Min Range: -7.8031
Max Act: 6.9594. Min Act: -0.1700
Data Index: 5024980 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8031. Min Range: -7.8031
Max Act: 6.9594. Min Act: -0.1700
Data Index: 1387343 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8031. Min Range: -7.8031
Max Act: 6.9281. Min Act: -0.1700
Data Index: 6778141 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8031. Min Range: -7.8031
Max Act: 6.9281. Min Act: -0.1700
Data Index: 8254640 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8031. Min Range: -7.8031
Max Act: 6.8969. Min Act: -0.1700
Data Index: 4565221 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8031. Min Range: -7.8031
Max Act: 6.8656. Min Act: -0.1700
Data Index: 4796176 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8031. Min Range: -7.8031
Max Act: 6.8969. Min Act: -0.1700
Data Index: 5629908 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19