Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 483 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2650. Min Act: -0.0002

Data Index: 884058 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2553. Min Act: -0.0002

Data Index: 263833 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2473. Min Act: -0.0002

Data Index: 267898 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2380. Min Act: -0.0002

Data Index: 806804 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2228. Min Act: -0.0002

Data Index: 970585 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2340. Min Act: -0.0002

Data Index: 204287 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2284. Min Act: -0.0002

Data Index: 554264 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2421. Min Act: -0.0002

Data Index: 1303162 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2325. Min Act: -0.0002

Data Index: 1254373 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2144. Min Act: -0.0002

Data Index: 972746 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2243. Min Act: -0.0002

Data Index: 721901 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2219. Min Act: -0.0002

Data Index: 629850 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2152. Min Act: -0.0002

Data Index: 1125561 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2349. Min Act: -0.0002

Data Index: 348844 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2274. Min Act: -0.0002

Data Index: 1350368 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2170. Min Act: -0.0002

Data Index: 547510 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2095. Min Act: -0.0002

Data Index: 377995 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2159. Min Act: -0.0002

Data Index: 860635 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2206. Min Act: -0.0002

Data Index: 662229 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2051. Min Act: -0.0002

Data Index: 885012 (C4 (Web Text))

Max Activating Token Index: 687