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

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

Neuron 3641 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: 0.3023. Min Range: -0.3023

Max Act: 0.3023. Min Act: -0.0001

Data Index: 1140732 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2908. Min Act: -0.0001

Data Index: 1305623 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2330. Min Act: -0.0001

Data Index: 191219 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2473. Min Act: -0.0001

Data Index: 1179170 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2457. Min Act: -0.0001

Data Index: 1267020 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2345. Min Act: -0.0000

Data Index: 422457 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2389. Min Act: -0.0001

Data Index: 1007394 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2378. Min Act: -0.0000

Data Index: 143904 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1150658 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2441. Min Act: -0.0001

Data Index: 109598 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2254. Min Act: -0.0001

Data Index: 710337 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2484. Min Act: -0.0001

Data Index: 543856 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2293. Min Act: -0.0001

Data Index: 553889 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2380. Min Act: -0.0000

Data Index: 918823 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2290. Min Act: -0.0001

Data Index: 800426 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2249. Min Act: -0.0000

Data Index: 373007 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2244. Min Act: -0.0001

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2337. Min Act: -0.0001

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2138. Min Act: -0.0000

Data Index: 65050 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2215. Min Act: -0.0001

Data Index: 59864 (C4 (Web Text))

Max Activating Token Index: 482