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

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

Neuron 4941 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5675. Min Act: -0.0000

Data Index: 594566 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5369. Min Act: -0.0000

Data Index: 669675 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.3919. Min Act: -0.0000

Data Index: 50661 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.4469. Min Act: -0.0000

Data Index: 1356242 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.4360. Min Act: -0.0000

Data Index: 59242 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5183. Min Act: -0.0000

Data Index: 1255269 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.4173. Min Act: -0.0000

Data Index: 1261026 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.4061. Min Act: -0.0000

Data Index: 647306 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.4767. Min Act: -0.0000

Data Index: 164019 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.3015. Min Act: -0.0000

Data Index: 412266 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.3578. Min Act: -0.0000

Data Index: 1106632 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.3542. Min Act: -0.0000

Data Index: 1312132 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.3073. Min Act: -0.0000

Data Index: 378179 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.3128. Min Act: -0.0000

Data Index: 1166410 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.2916. Min Act: -0.0000

Data Index: 274308 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.2219. Min Act: -0.0000

Data Index: 402462 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.2857. Min Act: -0.0000

Data Index: 327324 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1323321 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.2645. Min Act: -0.0000

Data Index: 324749 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.2596. Min Act: -0.0000

Data Index: 719649 (C4 (Web Text))

Max Activating Token Index: 803