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

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

Neuron 3983 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.8203. Min Act: -0.0000

Data Index: 1219437 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.8467. Min Act: 0.0000

Data Index: 443113 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.8487. Min Act: -0.0000

Data Index: 390468 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.8179. Min Act: -0.0000

Data Index: 948467 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1105580 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.7488. Min Act: -0.0000

Data Index: 605895 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.7193. Min Act: -0.0000

Data Index: 939812 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.7110. Min Act: 0.0000

Data Index: 1220246 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.6242. Min Act: -0.0000

Data Index: 974053 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.6626. Min Act: -0.0000

Data Index: 447839 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.6857. Min Act: 0.0000

Data Index: 224451 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.6729. Min Act: 0.0000

Data Index: 625153 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.6624. Min Act: 0.0000

Data Index: 368749 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.6623. Min Act: -0.0000

Data Index: 530324 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.6490. Min Act: -0.0000

Data Index: 971111 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1053846 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1304461 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.6319. Min Act: 0.0000

Data Index: 694901 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.6314. Min Act: -0.0000

Data Index: 189368 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.8487. Min Range: -0.8487

Max Act: 0.6546. Min Act: -0.0000

Data Index: 868160 (C4 (Web Text))

Max Activating Token Index: 552