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

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

Neuron 1195 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0441. Min Act: -0.0000

Data Index: 22860 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0120. Min Act: -0.0000

Data Index: 1002851 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9491. Min Act: -0.0000

Data Index: 56138 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8151. Min Act: -0.0000

Data Index: 391601 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8488. Min Act: -0.0000

Data Index: 374882 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8679. Min Act: -0.0000

Data Index: 548487 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8042. Min Act: -0.0000

Data Index: 160157 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7821. Min Act: -0.0000

Data Index: 373740 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7541. Min Act: -0.0001

Data Index: 526973 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7223. Min Act: -0.0000

Data Index: 909838 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1340852 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7453. Min Act: -0.0000

Data Index: 545518 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7781. Min Act: -0.0000

Data Index: 209315 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1209961 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7140. Min Act: -0.0000

Data Index: 172126 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7174. Min Act: -0.0000

Data Index: 59543 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7149. Min Act: -0.0000

Data Index: 452353 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1318816 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7043. Min Act: -0.0000

Data Index: 588076 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7221. Min Act: -0.0000

Data Index: 32670 (C4 (Web Text))

Max Activating Token Index: 115