Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5460 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0606. Min Act: -0.0000

Data Index: 767863 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0632. Min Act: -0.0001

Data Index: 962189 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0563. Min Act: -0.0001

Data Index: 527057 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0520. Min Act: -0.0000

Data Index: 729659 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0393. Min Act: -0.0000

Data Index: 582495 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0463. Min Act: -0.0001

Data Index: 212792 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0483. Min Act: -0.0000

Data Index: 132814 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0443. Min Act: -0.0001

Data Index: 713087 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0492. Min Act: -0.0000

Data Index: 459286 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0489. Min Act: -0.0001

Data Index: 494868 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0375. Min Act: -0.0000

Data Index: 757340 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0427. Min Act: -0.0000

Data Index: 22816 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0399. Min Act: -0.0000

Data Index: 971239 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0383. Min Act: -0.0000

Data Index: 357605 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1086674 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0424. Min Act: -0.0001

Data Index: 350926 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1137140 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0364. Min Act: -0.0000

Data Index: 485480 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0386. Min Act: -0.0000

Data Index: 497874 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0421. Min Act: -0.0000

Data Index: 617737 (C4 (Web Text))

Max Activating Token Index: 438