Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2888 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.8108. Min Act: -0.1700
Data Index: 1719967 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.6858. Min Act: -0.1700
Data Index: 5533012 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.6546. Min Act: -0.1700
Data Index: 4221972 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.6233. Min Act: -0.1700
Data Index: 5734069 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.6233. Min Act: -0.1700
Data Index: 7173995 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.5296. Min Act: -0.1700
Data Index: 1898351 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.4671. Min Act: -0.1700
Data Index: 7609039 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.4671. Min Act: -0.1700
Data Index: 7931924 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.4671. Min Act: -0.1700
Data Index: 5956586 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.4671. Min Act: -0.1700
Data Index: 8087118 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.4358. Min Act: -0.1700
Data Index: 4936346 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.4358. Min Act: -0.1700
Data Index: 1571430 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.4046. Min Act: -0.1700
Data Index: 1427790 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.3733. Min Act: -0.1700
Data Index: 4703318 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.3421. Min Act: -0.1700
Data Index: 7899642 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.3733. Min Act: -0.1700
Data Index: 452827 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.3421. Min Act: -0.1700
Data Index: 6014262 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.3421. Min Act: -0.1700
Data Index: 448380 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.3421. Min Act: -0.1700
Data Index: 4316207 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8108. Min Range: -5.8108
Max Act: 5.3733. Min Act: -0.1700
Data Index: 5910231 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19