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

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

Neuron 2338 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.5588. Min Act: -0.0000

Data Index: 151675 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.3650. Min Act: -0.0000

Data Index: 1279820 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.4206. Min Act: -0.0000

Data Index: 900278 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.2598. Min Act: -0.0000

Data Index: 672149 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.2158. Min Act: -0.0000

Data Index: 134206 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.1388. Min Act: -0.0000

Data Index: 151009 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.1927. Min Act: -0.0000

Data Index: 446114 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.1768. Min Act: -0.0000

Data Index: 6966 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.0907. Min Act: -0.0000

Data Index: 521330 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.1481. Min Act: -0.0000

Data Index: 826701 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.0714. Min Act: -0.0000

Data Index: 649859 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.0638. Min Act: -0.0000

Data Index: 1065610 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.1235. Min Act: -0.0000

Data Index: 1637605 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.1221. Min Act: -0.0000

Data Index: 276380 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1623825 (Python Code)

Max Activating Token Index: 691

Text #15

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.0321. Min Act: -0.0000

Data Index: 268879 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.0355. Min Act: -0.0000

Data Index: 953573 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.0982. Min Act: -0.0000

Data Index: 197236 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.0344. Min Act: -0.0000

Data Index: 965666 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.0894. Min Act: -0.0000

Data Index: 588481 (C4 (Web Text))

Max Activating Token Index: 1007