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

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

Neuron 5524 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5735. Min Range: -4.5735

Max Act: 4.5365. Min Act: -0.0000

Data Index: 1151094 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 4.5735. Min Range: -4.5735

Max Act: 4.5735. Min Act: -0.0000

Data Index: 393054 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 4.5735. Min Range: -4.5735

Max Act: 4.5032. Min Act: -0.0000

Data Index: 1001618 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 4.5735. Min Range: -4.5735

Max Act: 4.4322. Min Act: -0.0000

Data Index: 1144191 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 4.5735. Min Range: -4.5735

Max Act: 4.1677. Min Act: -0.0000

Data Index: 1190752 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.9878. Min Act: -0.0000

Data Index: 548181 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.9241. Min Act: -0.0000

Data Index: 1120583 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 4.5735. Min Range: -4.5735

Max Act: 4.0898. Min Act: -0.0000

Data Index: 765111 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.9110. Min Act: -0.0000

Data Index: 2031 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 4.5735. Min Range: -4.5735

Max Act: 4.0331. Min Act: -0.0000

Data Index: 594042 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.8891. Min Act: -0.0000

Data Index: 773712 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.8838. Min Act: -0.0000

Data Index: 530130 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.8363. Min Act: -0.0000

Data Index: 1336124 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.8379. Min Act: -0.0000

Data Index: 236042 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.7947. Min Act: -0.0000

Data Index: 493708 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.7375. Min Act: -0.0000

Data Index: 538546 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.4020. Min Act: -0.0000

Data Index: 1075460 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.6944. Min Act: -0.0000

Data Index: 1113134 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.7006. Min Act: -0.0000

Data Index: 848181 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 4.5735. Min Range: -4.5735

Max Act: 3.8109. Min Act: -0.0000

Data Index: 333651 (C4 (Web Text))

Max Activating Token Index: 738