Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1856 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0328. Min Act: -0.0003

Data Index: 839840 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0326. Min Act: -0.0004

Data Index: 395285 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0328. Min Act: -0.0004

Data Index: 919156 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1058445 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0319. Min Act: -0.0003

Data Index: 109296 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1092411 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0305. Min Act: -0.0003

Data Index: 492317 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0292. Min Act: -0.0003

Data Index: 56933 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0304. Min Act: -0.0003

Data Index: 221734 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0295. Min Act: -0.0004

Data Index: 603967 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0306. Min Act: -0.0003

Data Index: 745275 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0297. Min Act: -0.0003

Data Index: 643200 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0286. Min Act: -0.0003

Data Index: 237572 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1215358 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0298. Min Act: -0.0003

Data Index: 382561 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0307. Min Act: -0.0003

Data Index: 4042 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0296. Min Act: -0.0004

Data Index: 771947 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0296. Min Act: -0.0004

Data Index: 1180248 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0292. Min Act: -0.0004

Data Index: 557112 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0299. Min Act: -0.0003

Data Index: 570120 (C4 (Web Text))

Max Activating Token Index: 1021