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

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

Neuron 475 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3625. Min Act: -0.0000

Data Index: 924328 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3256. Min Act: 0.0000

Data Index: 576369 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1132075 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2691. Min Act: -0.0000

Data Index: 708733 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2441. Min Act: -0.0000

Data Index: 858428 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1077280 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2520. Min Act: -0.0000

Data Index: 311716 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2480. Min Act: -0.0000

Data Index: 21491 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2333. Min Act: 0.0000

Data Index: 531864 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2248. Min Act: -0.0000

Data Index: 327521 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2385. Min Act: -0.0000

Data Index: 946431 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2203. Min Act: -0.0000

Data Index: 459113 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1264621 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2145. Min Act: -0.0000

Data Index: 788146 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2047. Min Act: -0.0000

Data Index: 733804 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2123. Min Act: -0.0000

Data Index: 803022 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2090. Min Act: -0.0000

Data Index: 241545 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2175. Min Act: -0.0000

Data Index: 19855 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1260291 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.1912. Min Act: -0.0000

Data Index: 252631 (C4 (Web Text))

Max Activating Token Index: 783