Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2013 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.7230. Min Act: -0.1700
Data Index: 975313 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.7230. Min Act: -0.1700
Data Index: 6616890 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.6605. Min Act: -0.1700
Data Index: 5530301 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.6605. Min Act: -0.1700
Data Index: 327996 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.6292. Min Act: -0.1700
Data Index: 3672104 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.6292. Min Act: -0.1700
Data Index: 8408721 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.6292. Min Act: -0.1700
Data Index: 1897367 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.5667. Min Act: -0.1700
Data Index: 8622809 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.5667. Min Act: -0.1700
Data Index: 8756175 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.5355. Min Act: -0.1700
Data Index: 269201 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.5355. Min Act: -0.1700
Data Index: 4621530 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.5042. Min Act: -0.1700
Data Index: 8719381 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.5042. Min Act: -0.1700
Data Index: 518748 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.5042. Min Act: -0.1700
Data Index: 6230678 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.5042. Min Act: -0.1700
Data Index: 4308413 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.5042. Min Act: -0.1700
Data Index: 5626954 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.5042. Min Act: -0.1700
Data Index: 5609260 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.5042. Min Act: -0.1700
Data Index: 742403 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.4730. Min Act: -0.1700
Data Index: 3832799 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7230. Min Range: -4.7230
Max Act: 4.4417. Min Act: -0.1700
Data Index: 4375508 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19