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

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

Neuron 5031 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.3101. Min Act: -0.0000

Data Index: 730911 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.3033. Min Act: -0.0000

Data Index: 860505 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1301218 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1302314 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1130851 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1356041 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2820. Min Act: -0.0000

Data Index: 499389 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2753. Min Act: -0.0000

Data Index: 267623 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2796. Min Act: -0.0000

Data Index: 189826 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1054184 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2678. Min Act: -0.0000

Data Index: 905489 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2616. Min Act: -0.0000

Data Index: 344946 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1262398 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2561. Min Act: -0.0000

Data Index: 260294 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2622. Min Act: -0.0000

Data Index: 664264 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1111828 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2575. Min Act: -0.0000

Data Index: 843434 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1081495 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2552. Min Act: -0.0000

Data Index: 965540 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1259016 (C4 (Web Text))

Max Activating Token Index: 220