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

Dataset: The Pile

Neuron 1234 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: 1.3528. Min Range: -1.3528

Max Act: 1.3528. Min Act: -0.0000

Data Index: 512725 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0599. Min Act: -0.0000

Data Index: 1944778 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0448. Min Act: -0.0000

Data Index: 534490 (The Pile)

Max Activating Token Index: 250

Text #3

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0159. Min Act: -0.0000

Data Index: 619587 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1532093 (The Pile)

Max Activating Token Index: 746

Text #5

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0338. Min Act: -0.0000

Data Index: 1959115 (The Pile)

Max Activating Token Index: 351

Text #6

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1186462 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1984795 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1987685 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1758380 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.9866. Min Act: -0.0000

Data Index: 135737 (The Pile)

Max Activating Token Index: 947

Text #11

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.8354. Min Act: -0.0000

Data Index: 961755 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.8309. Min Act: -0.0000

Data Index: 290144 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.9031. Min Act: -0.0000

Data Index: 458395 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.8420. Min Act: -0.0000

Data Index: 4972 (The Pile)

Max Activating Token Index: 586

Text #15

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.8892. Min Act: -0.0000

Data Index: 638231 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.8175. Min Act: -0.0000

Data Index: 308274 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1806582 (The Pile)

Max Activating Token Index: 811

Text #18

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1921836 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.7740. Min Act: -0.0000

Data Index: 671468 (The Pile)

Max Activating Token Index: 170