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

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

Neuron 2274 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: 0.0724. Min Range: -0.0724

Max Act: 0.0563. Min Act: -0.0000

Data Index: 472474 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0566. Min Act: -0.0001

Data Index: 134128 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0445. Min Act: -0.0001

Data Index: 398340 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0495. Min Act: -0.0001

Data Index: 68092 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1628714 (Python Code)

Max Activating Token Index: 727

Text #5

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1194519 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1336483 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0508. Min Act: -0.0000

Data Index: 18386 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0463. Min Act: -0.0001

Data Index: 280734 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0345. Min Act: -0.0001

Data Index: 709465 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1317741 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0385. Min Act: -0.0000

Data Index: 725275 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1027947 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0214. Min Act: -0.0001

Data Index: 64249 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0425. Min Act: -0.0000

Data Index: 297032 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0724. Min Act: -0.0001

Data Index: 826484 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1338118 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0335. Min Act: -0.0001

Data Index: 285557 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0380. Min Act: -0.0000

Data Index: 69590 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0385. Min Act: -0.0000

Data Index: 277079 (C4 (Web Text))

Max Activating Token Index: 212