Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 803 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2921. Min Act: -0.0000

Data Index: 270003 (The Pile)

Max Activating Token Index: 901

Text #1

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1376281 (The Pile)

Max Activating Token Index: 408

Text #2

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.3212. Min Act: -0.0000

Data Index: 48540 (The Pile)

Max Activating Token Index: 916

Text #3

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2572. Min Act: -0.0000

Data Index: 299248 (The Pile)

Max Activating Token Index: 476

Text #4

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1671517 (The Pile)

Max Activating Token Index: 760

Text #5

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1223716 (The Pile)

Max Activating Token Index: 927

Text #6

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1755. Min Act: -0.0000

Data Index: 40377 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1801. Min Act: -0.0000

Data Index: 115025 (The Pile)

Max Activating Token Index: 790

Text #8

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1763. Min Act: -0.0000

Data Index: 843240 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1365994 (The Pile)

Max Activating Token Index: 664

Text #10

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1824373 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1525999 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1365191 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1237677 (The Pile)

Max Activating Token Index: 141

Text #14

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1990959 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1627913 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1649. Min Act: -0.0000

Data Index: 378917 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1845168 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1413. Min Act: -0.0000

Data Index: 545656 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1388375 (The Pile)

Max Activating Token Index: 302