Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4744 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.2359. Min Act: 0.0000

Data Index: 375074 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1540. Min Act: -0.0000

Data Index: 1070427 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.2178. Min Act: -0.0000

Data Index: 1147656 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.2365. Min Act: -0.0000

Data Index: 379139 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.2205. Min Act: -0.0000

Data Index: 612064 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1514. Min Act: -0.0000

Data Index: 1296051 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1199. Min Act: -0.0000

Data Index: 92122 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1111. Min Act: -0.0000

Data Index: 549699 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1027. Min Act: -0.0000

Data Index: 399756 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0947. Min Act: -0.0000

Data Index: 1298894 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1067418 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1356. Min Act: -0.0000

Data Index: 32751 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0575. Min Act: 0.0000

Data Index: 28676 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0393. Min Act: -0.0000

Data Index: 1065932 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0509. Min Act: -0.0000

Data Index: 689845 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1319. Min Act: -0.0000

Data Index: 672737 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9688. Min Act: -0.0000

Data Index: 1334155 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1325056 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 1.2365. Min Range: -1.2365

Max Act: 0.9147. Min Act: -0.0000

Data Index: 966178 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0265. Min Act: -0.0000

Data Index: 1150807 (C4 (Web Text))

Max Activating Token Index: 928