Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3946 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0013. Min Range: -7.0013
Max Act: 7.0013. Min Act: -0.1700
Data Index: 1425421 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.9075. Min Act: -0.1700
Data Index: 4927391 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.7513. Min Act: -0.1700
Data Index: 3271506 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.6575. Min Act: -0.1700
Data Index: 5088049 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.6575. Min Act: -0.1700
Data Index: 4798575 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.6263. Min Act: -0.1700
Data Index: 1575975 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.5638. Min Act: -0.1700
Data Index: 5936921 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.5638. Min Act: -0.1700
Data Index: 6229102 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.5638. Min Act: -0.1700
Data Index: 5443346 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.5325. Min Act: -0.1700
Data Index: 4548652 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.5325. Min Act: -0.1700
Data Index: 6719097 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.5638. Min Act: -0.1700
Data Index: 5204291 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.5325. Min Act: -0.1700
Data Index: 2100869 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.5013. Min Act: -0.1700
Data Index: 4693636 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.5013. Min Act: -0.1700
Data Index: 5622557 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.5013. Min Act: -0.1700
Data Index: 103663 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.4700. Min Act: -0.1700
Data Index: 7635114 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.4700. Min Act: -0.1700
Data Index: 2416334 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.4700. Min Act: -0.1700
Data Index: 5726805 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0013. Min Range: -7.0013
Max Act: 6.4388. Min Act: -0.1700
Data Index: 2906677 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19