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

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

Neuron 2364 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3649. Min Act: -0.0001

Data Index: 72412 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3157. Min Act: -0.0001

Data Index: 1337214 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3873. Min Act: -0.0001

Data Index: 380361 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2985. Min Act: -0.0001

Data Index: 1294593 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2989. Min Act: -0.0001

Data Index: 924038 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2724. Min Act: -0.0001

Data Index: 1195132 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2494. Min Act: -0.0001

Data Index: 622972 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2673. Min Act: -0.0001

Data Index: 1001838 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2527. Min Act: -0.0001

Data Index: 785432 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2494. Min Act: -0.0001

Data Index: 725894 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2671. Min Act: -0.0001

Data Index: 118195 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1286577 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2450. Min Act: -0.0001

Data Index: 668075 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2405. Min Act: -0.0001

Data Index: 682222 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2231. Min Act: -0.0001

Data Index: 858134 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2461. Min Act: -0.0000

Data Index: 424408 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2323. Min Act: -0.0001

Data Index: 44585 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2279. Min Act: -0.0001

Data Index: 1185511 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2241. Min Act: -0.0001

Data Index: 709468 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2236. Min Act: -0.0001

Data Index: 399178 (C4 (Web Text))

Max Activating Token Index: 181