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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5021 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2424. Min Act: -0.0000

Data Index: 893161 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2380. Min Act: -0.0000

Data Index: 828227 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2451. Min Act: -0.0000

Data Index: 598017 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2382. Min Act: -0.0000

Data Index: 445760 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2319. Min Act: -0.0000

Data Index: 399814 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1081099 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2222. Min Act: -0.0000

Data Index: 71820 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2244. Min Act: -0.0000

Data Index: 839942 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2122. Min Act: -0.0000

Data Index: 573956 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2282. Min Act: -0.0000

Data Index: 959175 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2170. Min Act: -0.0000

Data Index: 401905 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2080. Min Act: -0.0000

Data Index: 78028 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2159. Min Act: -0.0000

Data Index: 699514 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2108. Min Act: -0.0000

Data Index: 918372 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2187. Min Act: -0.0000

Data Index: 848771 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2041. Min Act: -0.0000

Data Index: 664810 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2189. Min Act: -0.0000

Data Index: 83877 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2155. Min Act: -0.0000

Data Index: 465820 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2087. Min Act: -0.0000

Data Index: 533217 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.2451. Min Range: -0.2451

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1357151 (C4 (Web Text))

Max Activating Token Index: 27