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

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

Neuron 2434 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.9405. Min Act: -0.0001

Data Index: 1643822 (Python Code)

Max Activating Token Index: 575

Text #1

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.9165. Min Act: -0.0001

Data Index: 1390568 (Python Code)

Max Activating Token Index: 215

Text #2

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8751. Min Act: -0.0001

Data Index: 1454432 (Python Code)

Max Activating Token Index: 779

Text #3

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.9430. Min Act: -0.0001

Data Index: 46491 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8554. Min Act: -0.0001

Data Index: 1544719 (Python Code)

Max Activating Token Index: 728

Text #5

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.9171. Min Act: -0.0001

Data Index: 309811 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8742. Min Act: -0.0001

Data Index: 1377857 (Python Code)

Max Activating Token Index: 648

Text #7

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8454. Min Act: -0.0001

Data Index: 1532200 (Python Code)

Max Activating Token Index: 582

Text #8

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7948. Min Act: -0.0001

Data Index: 1586103 (Python Code)

Max Activating Token Index: 688

Text #9

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8917. Min Act: -0.0001

Data Index: 1634210 (Python Code)

Max Activating Token Index: 695

Text #10

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8304. Min Act: -0.0001

Data Index: 591736 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8632. Min Act: -0.0001

Data Index: 1598784 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7817. Min Act: -0.0001

Data Index: 1571752 (Python Code)

Max Activating Token Index: 127

Text #13

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8241. Min Act: -0.0001

Data Index: 1165976 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7648. Min Act: -0.0001

Data Index: 1382062 (Python Code)

Max Activating Token Index: 474

Text #15

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7941. Min Act: -0.0001

Data Index: 262538 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8152. Min Act: -0.0001

Data Index: 1599724 (Python Code)

Max Activating Token Index: 627

Text #17

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8141. Min Act: -0.0001

Data Index: 619375 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7370. Min Act: -0.0001

Data Index: 708758 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7344. Min Act: -0.0001

Data Index: 1634213 (Python Code)

Max Activating Token Index: 787