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

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

Neuron 4741 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: 0.8629. Min Range: -0.8629

Max Act: 0.8629. Min Act: -0.0001

Data Index: 748958 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6687. Min Act: -0.0000

Data Index: 371954 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6259. Min Act: -0.0001

Data Index: 1175746 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6567. Min Act: -0.0001

Data Index: 145425 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5942. Min Act: -0.0001

Data Index: 1068517 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6551. Min Act: -0.0000

Data Index: 579526 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6502. Min Act: -0.0001

Data Index: 1239738 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1023257 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5626. Min Act: -0.0000

Data Index: 193590 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5827. Min Act: -0.0001

Data Index: 851687 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5383. Min Act: -0.0001

Data Index: 1572617 (Python Code)

Max Activating Token Index: 69

Text #11

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5864. Min Act: -0.0000

Data Index: 162204 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5381. Min Act: -0.0001

Data Index: 1369990 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5234. Min Act: -0.0001

Data Index: 364923 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6265. Min Act: -0.0001

Data Index: 1096137 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5358. Min Act: -0.0001

Data Index: 1541315 (Python Code)

Max Activating Token Index: 380

Text #16

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5964. Min Act: -0.0000

Data Index: 904999 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5511. Min Act: -0.0000

Data Index: 870987 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5498. Min Act: -0.0001

Data Index: 811487 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5545. Min Act: -0.0001

Data Index: 240440 (C4 (Web Text))

Max Activating Token Index: 425