Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3856 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6879. Min Act: -0.0000

Data Index: 55932 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6386. Min Act: -0.0000

Data Index: 361078 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6319. Min Act: -0.0000

Data Index: 36174 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6600. Min Act: -0.0000

Data Index: 565261 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5655. Min Act: -0.0000

Data Index: 995966 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6281. Min Act: -0.0000

Data Index: 640777 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6053. Min Act: -0.0000

Data Index: 219808 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1300645 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5245. Min Act: -0.0000

Data Index: 599203 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5380. Min Act: -0.0000

Data Index: 385383 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1028281 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5509. Min Act: -0.0000

Data Index: 918676 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5316. Min Act: -0.0000

Data Index: 421807 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5331. Min Act: -0.0000

Data Index: 109194 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5271. Min Act: -0.0000

Data Index: 186948 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.4908. Min Act: -0.0000

Data Index: 372104 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5141. Min Act: -0.0000

Data Index: 563343 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1230328 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1358592 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5250. Min Act: -0.0000

Data Index: 322192 (C4 (Web Text))

Max Activating Token Index: 458