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

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

Neuron 561 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2730. Min Act: -0.0000

Data Index: 759288 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1197740 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1098967 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2487. Min Act: -0.0000

Data Index: 890905 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2393. Min Act: -0.0001

Data Index: 856362 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2560. Min Act: -0.0000

Data Index: 843515 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2440. Min Act: -0.0000

Data Index: 443118 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2515. Min Act: -0.0000

Data Index: 13542 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2500. Min Act: -0.0000

Data Index: 681344 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2365. Min Act: -0.0000

Data Index: 378715 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2357. Min Act: -0.0000

Data Index: 897308 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2258. Min Act: -0.0000

Data Index: 901144 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2243. Min Act: -0.0000

Data Index: 218777 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2310. Min Act: -0.0000

Data Index: 534344 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2150. Min Act: -0.0000

Data Index: 764170 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.1921. Min Act: -0.0000

Data Index: 293413 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2293. Min Act: -0.0000

Data Index: 43394 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2137. Min Act: -0.0000

Data Index: 310129 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2078. Min Act: -0.0000

Data Index: 104308 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1004442 (C4 (Web Text))

Max Activating Token Index: 220