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

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

Neuron 1057 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: 0.1648. Min Range: -0.1648

Max Act: 0.1648. Min Act: -0.0002

Data Index: 804652 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1552. Min Act: -0.0002

Data Index: 884294 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1471. Min Act: -0.0002

Data Index: 1201164 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1448. Min Act: -0.0002

Data Index: 1030070 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1372. Min Act: -0.0002

Data Index: 209406 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1368. Min Act: -0.0002

Data Index: 566493 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1448. Min Act: -0.0002

Data Index: 39478 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1340. Min Act: -0.0002

Data Index: 127348 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1374. Min Act: -0.0002

Data Index: 420624 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1306. Min Act: -0.0002

Data Index: 989271 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1324. Min Act: -0.0002

Data Index: 10641 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1272. Min Act: -0.0002

Data Index: 859172 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1312. Min Act: -0.0002

Data Index: 902646 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1176. Min Act: -0.0002

Data Index: 746528 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1373. Min Act: -0.0002

Data Index: 406365 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1367. Min Act: -0.0002

Data Index: 91353 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1275. Min Act: -0.0002

Data Index: 492750 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1137. Min Act: -0.0002

Data Index: 596744 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1320293 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1324166 (C4 (Web Text))

Max Activating Token Index: 172