Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1280 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0337. Min Act: -0.0002

Data Index: 365534 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1111688 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1296611 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1466257 (Python Code)

Max Activating Token Index: 903

Text #4

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1579158 (Python Code)

Max Activating Token Index: 342

Text #5

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0219. Min Act: -0.0002

Data Index: 270215 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1391393 (Python Code)

Max Activating Token Index: 948

Text #7

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1361786 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1095410 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1406053 (Python Code)

Max Activating Token Index: 601

Text #10

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1275926 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0197. Min Act: -0.0002

Data Index: 926209 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0204. Min Act: -0.0002

Data Index: 43908 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1262235 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1502437 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0197. Min Act: -0.0002

Data Index: 455312 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0192. Min Act: -0.0002

Data Index: 23277 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1431894 (Python Code)

Max Activating Token Index: 777

Text #18

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0189. Min Act: -0.0002

Data Index: 718651 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1404673 (Python Code)

Max Activating Token Index: 379