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

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

Neuron 1346 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3568. Min Act: -0.0000

Data Index: 381733 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3284. Min Act: -0.0000

Data Index: 262800 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2771. Min Act: -0.0000

Data Index: 709050 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1082112 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2711. Min Act: -0.0000

Data Index: 424872 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2626. Min Act: -0.0000

Data Index: 916578 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2593. Min Act: -0.0000

Data Index: 726901 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2576. Min Act: -0.0000

Data Index: 209402 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1260350 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1244816 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2476. Min Act: -0.0000

Data Index: 208537 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2419. Min Act: -0.0000

Data Index: 423769 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1313311 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2480. Min Act: -0.0000

Data Index: 1331390 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2298. Min Act: -0.0000

Data Index: 762832 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2376. Min Act: -0.0000

Data Index: 873387 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2218. Min Act: -0.0000

Data Index: 211038 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2135. Min Act: -0.0000

Data Index: 723021 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1053272 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2110. Min Act: -0.0000

Data Index: 293941 (C4 (Web Text))

Max Activating Token Index: 492