Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1056 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1319740 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0218. Min Act: -0.0003

Data Index: 862157 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1052084 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0216. Min Act: -0.0003

Data Index: 690378 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0210. Min Act: -0.0003

Data Index: 904232 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0213. Min Act: -0.0003

Data Index: 514556 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1527887 (Python Code)

Max Activating Token Index: 899

Text #7

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0200. Min Act: -0.0003

Data Index: 1063507 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0190. Min Act: -0.0003

Data Index: 384412 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0191. Min Act: -0.0002

Data Index: 325442 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0190. Min Act: -0.0003

Data Index: 777011 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0197. Min Act: -0.0002

Data Index: 311068 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1225913 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0202. Min Act: -0.0003

Data Index: 869089 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0181. Min Act: -0.0003

Data Index: 112020 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1341574 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0201. Min Act: -0.0003

Data Index: 271982 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0182. Min Act: -0.0003

Data Index: 193191 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0189. Min Act: -0.0003

Data Index: 960297 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1005341 (C4 (Web Text))

Max Activating Token Index: 516