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

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

Neuron 979 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0346. Min Act: -0.0000

Data Index: 748105 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0343. Min Act: -0.0000

Data Index: 300475 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0349. Min Act: -0.0000

Data Index: 730514 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1240128 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0320. Min Act: -0.0001

Data Index: 530883 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0273. Min Act: -0.0000

Data Index: 577021 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0283. Min Act: -0.0000

Data Index: 445782 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0303. Min Act: -0.0000

Data Index: 539663 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0290. Min Act: -0.0000

Data Index: 181876 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0283. Min Act: -0.0000

Data Index: 617993 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1300971 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0299. Min Act: -0.0000

Data Index: 192455 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0277. Min Act: -0.0000

Data Index: 305370 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0283. Min Act: -0.0000

Data Index: 170586 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0262. Min Act: -0.0000

Data Index: 784808 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0280. Min Act: -0.0001

Data Index: 577585 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0264. Min Act: -0.0000

Data Index: 250059 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0265. Min Act: -0.0000

Data Index: 282880 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0283. Min Act: -0.0000

Data Index: 843167 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0273. Min Act: -0.0000

Data Index: 410254 (C4 (Web Text))

Max Activating Token Index: 33