Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 268 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6106. Min Range: -7.6106
Max Act: 7.6106. Min Act: -0.1700
Data Index: 677247 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6106. Min Range: -7.6106
Max Act: 7.4856. Min Act: -0.1700
Data Index: 3319711 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6106. Min Range: -7.6106
Max Act: 7.4231. Min Act: -0.1700
Data Index: 2005662 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6106. Min Range: -7.6106
Max Act: 7.4856. Min Act: -0.1700
Data Index: 1839243 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6106. Min Range: -7.6106
Max Act: 7.2044. Min Act: -0.1700
Data Index: 6445596 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6106. Min Range: -7.6106
Max Act: 7.1731. Min Act: -0.1700
Data Index: 1618153 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6106. Min Range: -7.6106
Max Act: 7.1419. Min Act: -0.1700
Data Index: 7946848 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6106. Min Range: -7.6106
Max Act: 7.0481. Min Act: -0.1700
Data Index: 7545345 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6106. Min Range: -7.6106
Max Act: 6.9856. Min Act: -0.1700
Data Index: 1845104 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6106. Min Range: -7.6106
Max Act: 6.9856. Min Act: -0.1700
Data Index: 2895390 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6106. Min Range: -7.6106
Max Act: 6.9231. Min Act: -0.1700
Data Index: 2916225 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6106. Min Range: -7.6106
Max Act: 6.8919. Min Act: -0.1700
Data Index: 3012807 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6106. Min Range: -7.6106
Max Act: 6.8606. Min Act: -0.1700
Data Index: 5000291 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6106. Min Range: -7.6106
Max Act: 6.8294. Min Act: -0.1700
Data Index: 8787304 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6106. Min Range: -7.6106
Max Act: 6.8294. Min Act: -0.1700
Data Index: 6400229 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6106. Min Range: -7.6106
Max Act: 6.7669. Min Act: -0.1700
Data Index: 7439500 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6106. Min Range: -7.6106
Max Act: 6.7669. Min Act: -0.1700
Data Index: 3053093 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6106. Min Range: -7.6106
Max Act: 6.7669. Min Act: -0.1700
Data Index: 8494101 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6106. Min Range: -7.6106
Max Act: 6.7356. Min Act: -0.1700
Data Index: 4768330 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6106. Min Range: -7.6106
Max Act: 6.7356. Min Act: -0.1700
Data Index: 7042100 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19