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

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

Neuron 1707 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1050316 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0563. Min Act: -0.0002

Data Index: 101375 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1199258 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0394. Min Act: -0.0002

Data Index: 396568 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0408. Min Act: -0.0002

Data Index: 955626 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1305934 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0438. Min Act: -0.0002

Data Index: 370511 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0469. Min Act: -0.0002

Data Index: 687074 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1371111 (Python Code)

Max Activating Token Index: 254

Text #9

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0329. Min Act: -0.0002

Data Index: 872800 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0370. Min Act: -0.0002

Data Index: 754864 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1118299 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1076102 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1610678 (Python Code)

Max Activating Token Index: 681

Text #14

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0378. Min Act: -0.0002

Data Index: 48694 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0378. Min Act: -0.0002

Data Index: 790517 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0359. Min Act: -0.0002

Data Index: 311803 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0378. Min Act: -0.0002

Data Index: 472394 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0425. Min Act: -0.0002

Data Index: 920778 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0422. Min Act: -0.0002

Data Index: 572480 (C4 (Web Text))

Max Activating Token Index: 588