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

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

Neuron 1229 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1160942 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1092024 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2864. Min Act: -0.0000

Data Index: 876613 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2580. Min Act: -0.0000

Data Index: 645874 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2445. Min Act: -0.0000

Data Index: 115021 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2408. Min Act: 0.0000

Data Index: 1214591 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2483. Min Act: -0.0000

Data Index: 189953 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2268. Min Act: -0.0000

Data Index: 380015 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1267230 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2397. Min Act: -0.0000

Data Index: 512102 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2300. Min Act: -0.0000

Data Index: 1464073 (Python Code)

Max Activating Token Index: 485

Text #11

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2345. Min Act: -0.0000

Data Index: 608497 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2254. Min Act: -0.0000

Data Index: 956431 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2311. Min Act: -0.0000

Data Index: 808537 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1151059 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2207. Min Act: -0.0000

Data Index: 661950 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2148. Min Act: -0.0001

Data Index: 875571 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2202. Min Act: -0.0000

Data Index: 774518 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1085184 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2211. Min Act: -0.0000

Data Index: 454021 (C4 (Web Text))

Max Activating Token Index: 531