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

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

Neuron 102 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: 0.2395. Min Range: -0.2395

Max Act: 0.2395. Min Act: -0.0001

Data Index: 510659 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2067. Min Act: -0.0000

Data Index: 841493 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1227383 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2034. Min Act: -0.0000

Data Index: 310348 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1959. Min Act: -0.0001

Data Index: 337601 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1099479 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1237027 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2066. Min Act: -0.0001

Data Index: 326596 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2078. Min Act: -0.0001

Data Index: 651506 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1947. Min Act: -0.0000

Data Index: 612791 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1877. Min Act: -0.0001

Data Index: 496147 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1982. Min Act: -0.0000

Data Index: 713111 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1888. Min Act: -0.0000

Data Index: 465241 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1876. Min Act: -0.0001

Data Index: 891273 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1862. Min Act: -0.0001

Data Index: 881718 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1948. Min Act: -0.0001

Data Index: 1298601 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1916. Min Act: -0.0001

Data Index: 675649 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1917. Min Act: -0.0000

Data Index: 968565 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1892. Min Act: -0.0000

Data Index: 327013 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1797. Min Act: -0.0000

Data Index: 473639 (C4 (Web Text))

Max Activating Token Index: 270