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

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

Neuron 168 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2758. Min Act: -0.0001

Data Index: 514355 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2784. Min Act: -0.0001

Data Index: 301300 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2443. Min Act: -0.0001

Data Index: 75451 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2395. Min Act: -0.0001

Data Index: 335752 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2362. Min Act: -0.0001

Data Index: 26052 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2480. Min Act: -0.0001

Data Index: 328222 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2367. Min Act: -0.0001

Data Index: 654986 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2518. Min Act: -0.0001

Data Index: 212505 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2205. Min Act: -0.0001

Data Index: 189525 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2250. Min Act: -0.0001

Data Index: 427697 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2148. Min Act: -0.0001

Data Index: 302454 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2185. Min Act: -0.0001

Data Index: 428957 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2241. Min Act: -0.0001

Data Index: 1219268 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1288878 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2212. Min Act: -0.0001

Data Index: 960085 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2222. Min Act: -0.0001

Data Index: 954008 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2234. Min Act: -0.0001

Data Index: 58938 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2347. Min Act: -0.0001

Data Index: 1295621 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2220. Min Act: -0.0001

Data Index: 981057 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2242. Min Act: -0.0001

Data Index: 1069860 (C4 (Web Text))

Max Activating Token Index: 903