Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3452 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1366. Min Range: -7.1366
Max Act: 7.1366. Min Act: -0.1700
Data Index: 4633395 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1366. Min Range: -7.1366
Max Act: 7.1053. Min Act: -0.1700
Data Index: 8678641 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1366. Min Range: -7.1366
Max Act: 7.0428. Min Act: -0.1700
Data Index: 941738 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1366. Min Range: -7.1366
Max Act: 7.0741. Min Act: -0.1700
Data Index: 245023 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1366. Min Range: -7.1366
Max Act: 7.0116. Min Act: -0.1700
Data Index: 1169185 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1366. Min Range: -7.1366
Max Act: 7.0428. Min Act: -0.1700
Data Index: 1691469 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1366. Min Range: -7.1366
Max Act: 7.0116. Min Act: -0.1700
Data Index: 1880541 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1366. Min Range: -7.1366
Max Act: 7.0428. Min Act: -0.1700
Data Index: 2238979 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1366. Min Range: -7.1366
Max Act: 6.9803. Min Act: -0.1700
Data Index: 4664825 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1366. Min Range: -7.1366
Max Act: 6.9491. Min Act: -0.1700
Data Index: 938864 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1366. Min Range: -7.1366
Max Act: 6.9491. Min Act: -0.1700
Data Index: 6908252 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1366. Min Range: -7.1366
Max Act: 6.9491. Min Act: -0.1700
Data Index: 1668676 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1366. Min Range: -7.1366
Max Act: 6.9491. Min Act: -0.1700
Data Index: 1035357 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1366. Min Range: -7.1366
Max Act: 6.9803. Min Act: -0.1700
Data Index: 6270554 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1366. Min Range: -7.1366
Max Act: 6.9178. Min Act: -0.1700
Data Index: 5966371 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1366. Min Range: -7.1366
Max Act: 6.9178. Min Act: -0.1700
Data Index: 1500400 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1366. Min Range: -7.1366
Max Act: 6.9178. Min Act: -0.1700
Data Index: 5400384 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1366. Min Range: -7.1366
Max Act: 6.9178. Min Act: -0.1700
Data Index: 7185539 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1366. Min Range: -7.1366
Max Act: 6.8866. Min Act: -0.1700
Data Index: 1634919 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1366. Min Range: -7.1366
Max Act: 6.8866. Min Act: -0.1700
Data Index: 826806 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19