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

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

Neuron 2727 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4503. Min Range: -4.4503

Max Act: 4.4503. Min Act: -0.0000

Data Index: 730365 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.3855. Min Act: -0.0000

Data Index: 430969 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.6302. Min Act: -0.0000

Data Index: 1343532 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.4683. Min Act: -0.0000

Data Index: 715552 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.2301. Min Act: -0.0000

Data Index: 223306 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.1897. Min Act: -0.0000

Data Index: 559077 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.4804. Min Act: -0.0000

Data Index: 979010 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.4476. Min Act: -0.0000

Data Index: 717390 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.2504. Min Act: -0.0000

Data Index: 63479 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.2679. Min Act: -0.0000

Data Index: 764732 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.2649. Min Act: -0.0000

Data Index: 982811 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.2134. Min Act: -0.0000

Data Index: 355471 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.2376. Min Act: -0.0000

Data Index: 391259 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.0303. Min Act: -0.0000

Data Index: 104264 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.1757. Min Act: -0.0000

Data Index: 387437 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.0139. Min Act: -0.0000

Data Index: 929234 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.1664. Min Act: -0.0000

Data Index: 1200517 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.2759. Min Act: -0.0000

Data Index: 139547 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.2612. Min Act: -0.0000

Data Index: 798593 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 4.4503. Min Range: -4.4503

Max Act: 3.2745. Min Act: -0.0000

Data Index: 671173 (C4 (Web Text))

Max Activating Token Index: 781