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

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

Neuron 3867 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2888. Min Act: -0.0003

Data Index: 265165 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2940. Min Act: -0.0003

Data Index: 244080 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2857. Min Act: -0.0003

Data Index: 260608 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2674. Min Act: -0.0002

Data Index: 566863 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2664. Min Act: -0.0003

Data Index: 1072365 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2573. Min Act: -0.0003

Data Index: 391559 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2513. Min Act: -0.0003

Data Index: 268643 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2510. Min Act: -0.0003

Data Index: 1355140 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2466. Min Act: -0.0003

Data Index: 885364 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2448. Min Act: -0.0003

Data Index: 249456 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2419. Min Act: -0.0003

Data Index: 1129303 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2414. Min Act: -0.0003

Data Index: 316544 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2381. Min Act: -0.0002

Data Index: 956525 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2352. Min Act: -0.0002

Data Index: 783568 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2338. Min Act: -0.0003

Data Index: 390263 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2161. Min Act: -0.0002

Data Index: 174874 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2294. Min Act: -0.0003

Data Index: 742969 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2098. Min Act: -0.0003

Data Index: 289317 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2250. Min Act: -0.0003

Data Index: 852326 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2198. Min Act: -0.0002

Data Index: 1086354 (C4 (Web Text))

Max Activating Token Index: 214