Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1272 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.6180. Min Act: -0.0000

Data Index: 937664 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.6306. Min Act: -0.0000

Data Index: 76541 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1244425 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5753. Min Act: -0.0000

Data Index: 584573 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5677. Min Act: -0.0000

Data Index: 496164 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5321. Min Act: -0.0000

Data Index: 581107 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5258. Min Act: -0.0000

Data Index: 86337 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5219. Min Act: -0.0001

Data Index: 33435 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5207. Min Act: -0.0000

Data Index: 752828 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5158. Min Act: -0.0000

Data Index: 26391 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4811. Min Act: -0.0001

Data Index: 431439 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4979. Min Act: -0.0001

Data Index: 1164454 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5033. Min Act: -0.0000

Data Index: 514879 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1076735 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4678. Min Act: -0.0001

Data Index: 719641 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4585. Min Act: -0.0000

Data Index: 719749 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1227087 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4700. Min Act: -0.0000

Data Index: 971509 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4638. Min Act: -0.0000

Data Index: 684609 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1286839 (C4 (Web Text))

Max Activating Token Index: 770