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

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

Neuron 3409 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: 0.0306. Min Range: -0.0306

Max Act: 0.0306. Min Act: -0.0002

Data Index: 238881 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1600260 (Python Code)

Max Activating Token Index: 981

Text #2

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1571432 (Python Code)

Max Activating Token Index: 498

Text #3

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0261. Min Act: -0.0001

Data Index: 610889 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0260. Min Act: -0.0001

Data Index: 1559064 (Python Code)

Max Activating Token Index: 949

Text #5

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1578198 (Python Code)

Max Activating Token Index: 524

Text #6

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0272. Min Act: -0.0001

Data Index: 682511 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1475637 (Python Code)

Max Activating Token Index: 943

Text #8

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1427010 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1335078 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1364187 (Python Code)

Max Activating Token Index: 686

Text #11

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1367863 (Python Code)

Max Activating Token Index: 554

Text #12

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1595814 (Python Code)

Max Activating Token Index: 500

Text #13

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0234. Min Act: -0.0001

Data Index: 349148 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1149095 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0242. Min Act: -0.0001

Data Index: 934977 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1105593 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0236. Min Act: -0.0001

Data Index: 1220011 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1372992 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1598556 (Python Code)

Max Activating Token Index: 769