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

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

Neuron 4105 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: 0.5213. Min Range: -0.5213

Max Act: 0.5213. Min Act: -0.0000

Data Index: 977513 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3678. Min Act: -0.0000

Data Index: 629014 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1520090 (Python Code)

Max Activating Token Index: 293

Text #3

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3431. Min Act: -0.0000

Data Index: 377410 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3580. Min Act: -0.0000

Data Index: 814481 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1191396 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3179. Min Act: -0.0000

Data Index: 355953 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3044. Min Act: -0.0000

Data Index: 307427 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1136323 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.2782. Min Act: -0.0000

Data Index: 155308 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.2950. Min Act: -0.0000

Data Index: 337935 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.2858. Min Act: -0.0000

Data Index: 270284 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1310827 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.2731. Min Act: -0.0000

Data Index: 553994 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.2763. Min Act: -0.0000

Data Index: 414572 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.2766. Min Act: -0.0000

Data Index: 296517 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1033998 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.2929. Min Act: -0.0000

Data Index: 353432 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.2833. Min Act: -0.0000

Data Index: 153064 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.2656. Min Act: -0.0000

Data Index: 441389 (C4 (Web Text))

Max Activating Token Index: 846