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

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

Neuron 1973 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.3583. Min Act: -0.0000

Data Index: 881473 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2756. Min Act: -0.0000

Data Index: 800183 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1349212 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2815. Min Act: 0.0000

Data Index: 177233 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1261145 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2681. Min Act: -0.0000

Data Index: 370807 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2763. Min Act: -0.0000

Data Index: 815193 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2481. Min Act: 0.0000

Data Index: 1082426 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2451. Min Act: -0.0001

Data Index: 1597799 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2351. Min Act: -0.0000

Data Index: 507215 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2563. Min Act: -0.0000

Data Index: 988276 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2288. Min Act: -0.0000

Data Index: 324476 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2427. Min Act: 0.0001

Data Index: 409463 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2240. Min Act: -0.0000

Data Index: 610242 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2330. Min Act: -0.0000

Data Index: 195622 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1417699 (Python Code)

Max Activating Token Index: 183

Text #16

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2164. Min Act: -0.0000

Data Index: 508600 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1052654 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2395. Min Act: -0.0000

Data Index: 828041 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2157. Min Act: -0.0000

Data Index: 403594 (C4 (Web Text))

Max Activating Token Index: 812