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

Dataset: The Pile

Neuron 3511 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1705139 (The Pile)

Max Activating Token Index: 789

Text #1

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2380. Min Act: -0.0000

Data Index: 129632 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1286577 (The Pile)

Max Activating Token Index: 968

Text #3

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1278690 (The Pile)

Max Activating Token Index: 549

Text #4

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2382. Min Act: -0.0000

Data Index: 213433 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1513411 (The Pile)

Max Activating Token Index: 266

Text #6

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1081967 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2046. Min Act: -0.0000

Data Index: 725887 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2119. Min Act: -0.0000

Data Index: 295045 (The Pile)

Max Activating Token Index: 506

Text #9

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1285121 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1005292 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1609552 (The Pile)

Max Activating Token Index: 748

Text #12

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2163. Min Act: -0.0000

Data Index: 601696 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1670004 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2059. Min Act: -0.0000

Data Index: 836872 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1966135 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2111. Min Act: -0.0001

Data Index: 216374 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2087. Min Act: -0.0000

Data Index: 288404 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2148. Min Act: -0.0000

Data Index: 31286 (The Pile)

Max Activating Token Index: 349

Text #19

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1362063 (The Pile)

Max Activating Token Index: 338