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

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

Neuron 324 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.3488. Min Act: -0.0000

Data Index: 361940 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.3548. Min Act: -0.0001

Data Index: 984261 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1005227 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2890. Min Act: -0.0000

Data Index: 304978 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2742. Min Act: -0.0000

Data Index: 940826 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2578. Min Act: -0.0000

Data Index: 760593 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2558. Min Act: -0.0001

Data Index: 160360 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2391. Min Act: -0.0001

Data Index: 1071023 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2293. Min Act: -0.0000

Data Index: 959717 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2250. Min Act: -0.0001

Data Index: 1419197 (Python Code)

Max Activating Token Index: 324

Text #10

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2290. Min Act: -0.0001

Data Index: 1069982 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1319157 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2406. Min Act: -0.0001

Data Index: 1372937 (Python Code)

Max Activating Token Index: 570

Text #13

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2236. Min Act: -0.0001

Data Index: 165464 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2215. Min Act: -0.0000

Data Index: 61620 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2259. Min Act: -0.0001

Data Index: 160311 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2170. Min Act: -0.0000

Data Index: 62844 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2099. Min Act: -0.0001

Data Index: 350025 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2145. Min Act: -0.0001

Data Index: 569296 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2164. Min Act: -0.0001

Data Index: 886728 (C4 (Web Text))

Max Activating Token Index: 581