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

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

Neuron 2063 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.4763. Min Act: -0.0000

Data Index: 171499 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.4387. Min Act: -0.0000

Data Index: 952564 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.4478. Min Act: -0.0001

Data Index: 193520 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.4052. Min Act: -0.0000

Data Index: 252767 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.4286. Min Act: -0.0000

Data Index: 598933 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1115828 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3970. Min Act: -0.0000

Data Index: 397405 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3774. Min Act: -0.0001

Data Index: 1227911 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3627. Min Act: -0.0001

Data Index: 219991 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3733. Min Act: -0.0000

Data Index: 813448 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3676. Min Act: -0.0000

Data Index: 361808 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1193966 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3458. Min Act: -0.0000

Data Index: 697987 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3538. Min Act: -0.0001

Data Index: 410845 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3415. Min Act: -0.0000

Data Index: 882599 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3623. Min Act: -0.0000

Data Index: 986100 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3586. Min Act: -0.0001

Data Index: 875059 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3543. Min Act: -0.0001

Data Index: 145798 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3529. Min Act: -0.0000

Data Index: 922119 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.4763. Min Range: -0.4763

Max Act: 0.3372. Min Act: -0.0001

Data Index: 398184 (C4 (Web Text))

Max Activating Token Index: 256