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

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

Neuron 3196 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: 2.4089. Min Range: -2.4089

Max Act: 2.4089. Min Act: -0.0000

Data Index: 828122 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 2.4089. Min Range: -2.4089

Max Act: 2.1142. Min Act: 0.0000

Data Index: 976638 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.7667. Min Act: -0.0000

Data Index: 229663 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.7076. Min Act: -0.0000

Data Index: 471586 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.7399. Min Act: -0.0000

Data Index: 71463 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.5174. Min Act: -0.0000

Data Index: 345481 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.5826. Min Act: -0.0000

Data Index: 851676 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.6651. Min Act: -0.0000

Data Index: 814000 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.6671. Min Act: -0.0000

Data Index: 666312 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.4450. Min Act: -0.0000

Data Index: 1028185 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.4010. Min Act: -0.0000

Data Index: 377990 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.3336. Min Act: -0.0000

Data Index: 369264 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.3909. Min Act: -0.0000

Data Index: 972997 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.4577. Min Act: -0.0000

Data Index: 605500 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.2901. Min Act: -0.0000

Data Index: 335392 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.3546. Min Act: -0.0000

Data Index: 46148 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1283155 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.4184. Min Act: -0.0000

Data Index: 34238 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.4695. Min Act: -0.0000

Data Index: 919506 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 2.4089. Min Range: -2.4089

Max Act: 1.3072. Min Act: -0.0000

Data Index: 261976 (C4 (Web Text))

Max Activating Token Index: 1008