Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1527 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4833. Min Act: -0.0001

Data Index: 1241799 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4325. Min Act: -0.0001

Data Index: 665105 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4275. Min Act: -0.0001

Data Index: 420944 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4374. Min Act: -0.0001

Data Index: 1345038 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4349. Min Act: -0.0001

Data Index: 1347985 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4450. Min Act: -0.0001

Data Index: 908438 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4164. Min Act: -0.0001

Data Index: 613943 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4157. Min Act: -0.0001

Data Index: 724379 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4269. Min Act: -0.0001

Data Index: 957985 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4009. Min Act: -0.0001

Data Index: 1048152 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4109. Min Act: -0.0001

Data Index: 888523 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4084. Min Act: -0.0001

Data Index: 147493 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4223. Min Act: -0.0001

Data Index: 1312921 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4209. Min Act: -0.0001

Data Index: 1151014 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4176. Min Act: -0.0001

Data Index: 64309 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4071. Min Act: -0.0001

Data Index: 1110755 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4162. Min Act: -0.0001

Data Index: 427681 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.3801. Min Act: -0.0001

Data Index: 151556 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4046. Min Act: -0.0001

Data Index: 349323 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.4833. Min Range: -0.4833

Max Act: 0.4145. Min Act: -0.0001

Data Index: 110220 (C4 (Web Text))

Max Activating Token Index: 76