Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 426 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.7985. Min Act: -0.0001
Data Index: 1472553 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8290. Min Act: -0.0001
Data Index: 1103604 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.9427. Min Act: -0.0001
Data Index: 710446 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.6790. Min Act: -0.0001
Data Index: 1155162 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.6715. Min Act: -0.0001
Data Index: 690475 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.6842. Min Act: -0.0001
Data Index: 1317743 (The Pile)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.7315. Min Act: -0.0001
Data Index: 218889 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.7445. Min Act: -0.0001
Data Index: 15533 (The Pile)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.6280. Min Act: -0.0001
Data Index: 413255 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.6183. Min Act: -0.0001
Data Index: 1738978 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.5623. Min Act: -0.0001
Data Index: 1207393 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.5646. Min Act: -0.0001
Data Index: 1344205 (The Pile)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.5718. Min Act: -0.0001
Data Index: 1842980 (The Pile)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.5221. Min Act: -0.0001
Data Index: 1339204 (The Pile)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.5543. Min Act: -0.0001
Data Index: 1895328 (The Pile)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.5696. Min Act: -0.0001
Data Index: 631856 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.6359. Min Act: -0.0001
Data Index: 535768 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.5649. Min Act: -0.0001
Data Index: 1538800 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.5265. Min Act: -0.0001
Data Index: 357904 (The Pile)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.6072. Min Act: -0.0001
Data Index: 266377 (The Pile)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19