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

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

Neuron 2384 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: 0.2817. Min Range: -0.2817

Max Act: 0.2817. Min Act: -0.0001

Data Index: 720849 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2347. Min Act: -0.0001

Data Index: 18441 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2480. Min Act: -0.0001

Data Index: 283306 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2282. Min Act: -0.0001

Data Index: 296416 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2446. Min Act: -0.0001

Data Index: 361439 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2266. Min Act: -0.0001

Data Index: 12456 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2208. Min Act: -0.0001

Data Index: 1043714 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2237. Min Act: -0.0001

Data Index: 1184380 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2241. Min Act: -0.0001

Data Index: 792499 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2128. Min Act: -0.0001

Data Index: 301484 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2128. Min Act: -0.0001

Data Index: 628661 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2221. Min Act: -0.0001

Data Index: 926202 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2227. Min Act: -0.0001

Data Index: 766163 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2153. Min Act: -0.0001

Data Index: 1296933 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2072. Min Act: -0.0001

Data Index: 746211 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2203. Min Act: -0.0001

Data Index: 797059 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2050. Min Act: -0.0000

Data Index: 886590 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2057. Min Act: -0.0001

Data Index: 118396 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2105. Min Act: -0.0001

Data Index: 1197618 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2084. Min Act: -0.0001

Data Index: 392545 (C4 (Web Text))

Max Activating Token Index: 380