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

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

Neuron 4309 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.3998. Min Act: -0.0000

Data Index: 889882 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.4247. Min Act: -0.0001

Data Index: 1253922 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.3515. Min Act: -0.0000

Data Index: 991639 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.3100. Min Act: -0.0000

Data Index: 798450 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.2868. Min Act: -0.0001

Data Index: 453937 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.2228. Min Act: -0.0000

Data Index: 923613 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.2289. Min Act: -0.0000

Data Index: 897809 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.2232. Min Act: -0.0000

Data Index: 59649 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.2157. Min Act: -0.0001

Data Index: 790022 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.2134. Min Act: -0.0001

Data Index: 435559 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.2222. Min Act: -0.0001

Data Index: 116960 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.1965. Min Act: -0.0000

Data Index: 89037 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.2209. Min Act: -0.0001

Data Index: 1030936 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.2180. Min Act: -0.0000

Data Index: 551147 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.1480. Min Act: -0.0001

Data Index: 1222379 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.2156. Min Act: -0.0000

Data Index: 1225914 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.1831. Min Act: -0.0001

Data Index: 896350 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.1384. Min Act: -0.0000

Data Index: 340426 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.1712. Min Act: -0.0001

Data Index: 418094 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 1.4247. Min Range: -1.4247

Max Act: 1.1469. Min Act: -0.0001

Data Index: 1102140 (C4 (Web Text))

Max Activating Token Index: 666