Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 889 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1609. Min Range: -7.1609
Max Act: 7.1609. Min Act: -0.1700
Data Index: 6987242 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1609. Min Range: -7.1609
Max Act: 7.1296. Min Act: -0.1700
Data Index: 1426269 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1609. Min Range: -7.1609
Max Act: 7.1296. Min Act: -0.1700
Data Index: 3495852 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1609. Min Range: -7.1609
Max Act: 7.0359. Min Act: -0.1700
Data Index: 3332487 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.9734. Min Act: -0.1700
Data Index: 6479383 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.9109. Min Act: -0.1700
Data Index: 1489898 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.9109. Min Act: -0.1700
Data Index: 6383689 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.8484. Min Act: -0.1700
Data Index: 304472 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.7859. Min Act: -0.1700
Data Index: 5003508 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.8484. Min Act: -0.1700
Data Index: 7714829 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.8171. Min Act: -0.1700
Data Index: 6477714 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.7859. Min Act: -0.1700
Data Index: 2772179 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.7859. Min Act: -0.1700
Data Index: 3686225 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.7859. Min Act: -0.1700
Data Index: 7937411 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.7546. Min Act: -0.1700
Data Index: 760231 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.7234. Min Act: -0.1700
Data Index: 2429971 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.7234. Min Act: -0.1700
Data Index: 3684321 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.7234. Min Act: -0.1700
Data Index: 3266515 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.7234. Min Act: -0.1700
Data Index: 3216948 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1609. Min Range: -7.1609
Max Act: 6.7234. Min Act: -0.1700
Data Index: 6293780 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19