Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1912 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1416959 (Python Code)

Max Activating Token Index: 562

Text #1

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0400. Min Act: -0.0001

Data Index: 1540051 (Python Code)

Max Activating Token Index: 718

Text #2

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0334. Min Act: -0.0001

Data Index: 791355 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1465093 (Python Code)

Max Activating Token Index: 415

Text #4

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0315. Min Act: -0.0001

Data Index: 536332 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0301. Min Act: -0.0002

Data Index: 925134 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0292. Min Act: -0.0002

Data Index: 934629 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0284. Min Act: -0.0001

Data Index: 1564283 (Python Code)

Max Activating Token Index: 297

Text #8

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1369797 (Python Code)

Max Activating Token Index: 818

Text #9

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1402167 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0281. Min Act: -0.0002

Data Index: 221426 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0272. Min Act: -0.0001

Data Index: 852698 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1313522 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1526043 (Python Code)

Max Activating Token Index: 429

Text #14

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1605877 (Python Code)

Max Activating Token Index: 177

Text #15

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0275. Min Act: -0.0002

Data Index: 966012 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1233186 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1403979 (Python Code)

Max Activating Token Index: 360

Text #18

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1105815 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1004062 (C4 (Web Text))

Max Activating Token Index: 171