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

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

Neuron 598 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.9272. Min Act: -0.0001

Data Index: 329604 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.7791. Min Act: -0.0000

Data Index: 680552 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.7889. Min Act: -0.0000

Data Index: 239104 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.8141. Min Act: -0.0000

Data Index: 229669 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1028832 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.7508. Min Act: -0.0001

Data Index: 1141994 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.7349. Min Act: -0.0000

Data Index: 502987 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.7344. Min Act: -0.0000

Data Index: 441293 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1225686 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.7176. Min Act: -0.0000

Data Index: 645999 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1085268 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.7263. Min Act: -0.0000

Data Index: 649457 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1145430 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.7365. Min Act: -0.0000

Data Index: 101204 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.6353. Min Act: -0.0000

Data Index: 23877 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.7020. Min Act: -0.0001

Data Index: 280678 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1642666 (Python Code)

Max Activating Token Index: 1017

Text #17

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1283512 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.6650. Min Act: -0.0000

Data Index: 494405 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.9272. Min Range: -0.9272

Max Act: 0.6613. Min Act: -0.0000

Data Index: 994274 (C4 (Web Text))

Max Activating Token Index: 989