Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1684. Min Act: -0.0002

Data Index: 1256671 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1641. Min Act: -0.0002

Data Index: 164513 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1562. Min Act: -0.0002

Data Index: 800115 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1393. Min Act: -0.0002

Data Index: 967283 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1392. Min Act: -0.0002

Data Index: 447398 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1333. Min Act: -0.0002

Data Index: 201105 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1364. Min Act: -0.0002

Data Index: 1338705 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1363. Min Act: -0.0002

Data Index: 646166 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1301. Min Act: -0.0002

Data Index: 1196211 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1299. Min Act: -0.0002

Data Index: 215129 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1231. Min Act: -0.0002

Data Index: 52836 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1272. Min Act: -0.0002

Data Index: 137770 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1248. Min Act: -0.0002

Data Index: 221474 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1251. Min Act: -0.0002

Data Index: 45780 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1241. Min Act: -0.0002

Data Index: 745027 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1202. Min Act: -0.0002

Data Index: 980980 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1187. Min Act: -0.0002

Data Index: 530571 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1194. Min Act: -0.0002

Data Index: 461001 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1125. Min Act: -0.0002

Data Index: 303330 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.1684. Min Range: -0.1684

Max Act: 0.1107. Min Act: -0.0002

Data Index: 1372403 (Python Code)

Max Activating Token Index: 613