Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1347 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.4383. Min Act: -0.0001

Data Index: 1269213 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.4234. Min Act: -0.0001

Data Index: 407146 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3964. Min Act: -0.0001

Data Index: 343430 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3970. Min Act: -0.0001

Data Index: 1084596 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3826. Min Act: -0.0001

Data Index: 754575 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3643. Min Act: -0.0001

Data Index: 302575 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3476. Min Act: -0.0001

Data Index: 1146233 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3680. Min Act: -0.0001

Data Index: 465945 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3535. Min Act: -0.0001

Data Index: 306847 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3448. Min Act: -0.0001

Data Index: 285687 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3264. Min Act: -0.0001

Data Index: 171662 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3342. Min Act: -0.0001

Data Index: 543392 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3166. Min Act: -0.0001

Data Index: 707395 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3291. Min Act: -0.0001

Data Index: 383366 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3380. Min Act: -0.0001

Data Index: 260016 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3337. Min Act: -0.0001

Data Index: 795586 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3271. Min Act: -0.0001

Data Index: 15692 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3061. Min Act: -0.0001

Data Index: 136996 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3173. Min Act: -0.0001

Data Index: 169310 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.4383. Min Range: -0.4383

Max Act: 0.3226. Min Act: -0.0001

Data Index: 399802 (C4 (Web Text))

Max Activating Token Index: 249