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

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

Neuron 2142 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.9351. Min Act: -0.0001

Data Index: 139796 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8441. Min Act: -0.0001

Data Index: 407828 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8429. Min Act: -0.0001

Data Index: 10066 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7928. Min Act: -0.0001

Data Index: 202763 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 1.0484. Min Range: -1.0484

Max Act: 1.0484. Min Act: -0.0001

Data Index: 236727 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8902. Min Act: -0.0001

Data Index: 812736 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8317. Min Act: -0.0001

Data Index: 1268418 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8230. Min Act: -0.0001

Data Index: 303572 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8254. Min Act: -0.0001

Data Index: 1028932 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8448. Min Act: -0.0001

Data Index: 653794 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8543. Min Act: -0.0001

Data Index: 498524 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7621. Min Act: -0.0001

Data Index: 477393 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7593. Min Act: -0.0001

Data Index: 996583 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7774. Min Act: -0.0001

Data Index: 995461 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7482. Min Act: -0.0001

Data Index: 633487 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7521. Min Act: -0.0001

Data Index: 579648 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7183. Min Act: -0.0001

Data Index: 701380 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7092. Min Act: -0.0001

Data Index: 154317 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7476. Min Act: -0.0001

Data Index: 592961 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7005. Min Act: -0.0001

Data Index: 940024 (C4 (Web Text))

Max Activating Token Index: 791