Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 102 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.3108. Min Act: -0.0004

Data Index: 921007 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.2241. Min Act: -0.0004

Data Index: 998319 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1827. Min Act: -0.0004

Data Index: 376240 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.3275. Min Act: -0.0004

Data Index: 1013368 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.2513. Min Act: -0.0004

Data Index: 256399 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1083. Min Act: -0.0004

Data Index: 1345581 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.2290. Min Act: -0.0004

Data Index: 1006115 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.2236. Min Act: -0.0004

Data Index: 808601 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1485. Min Act: -0.0004

Data Index: 1115314 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.2945. Min Act: -0.0004

Data Index: 1207173 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.2546. Min Act: -0.0004

Data Index: 652316 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1733. Min Act: -0.0004

Data Index: 774684 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.2780. Min Act: -0.0004

Data Index: 1242578 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1831. Min Act: -0.0004

Data Index: 43195 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.2172. Min Act: -0.0004

Data Index: 328140 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.2090. Min Act: -0.0004

Data Index: 231288 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1700. Min Act: -0.0004

Data Index: 140800 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1744. Min Act: -0.0004

Data Index: 1357356 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1947. Min Act: -0.0004

Data Index: 1335050 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0582. Min Act: -0.0004

Data Index: 105693 (C4 (Web Text))

Max Activating Token Index: 267