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

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

Neuron 660 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.7412. Min Act: -0.0000

Data Index: 964352 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.8440. Min Act: -0.0000

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.7510. Min Act: -0.0000

Data Index: 498274 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.7538. Min Act: -0.0000

Data Index: 888269 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1125404 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6042. Min Act: -0.0000

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.7458. Min Act: -0.0000

Data Index: 125956 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1646071 (Python Code)

Max Activating Token Index: 146

Text #8

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6969. Min Act: -0.0000

Data Index: 792877 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1313313 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1239563 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1093496 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6355. Min Act: -0.0000

Data Index: 421700 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6342. Min Act: -0.0000

Data Index: 192762 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6318. Min Act: -0.0000

Data Index: 531204 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5977. Min Act: -0.0000

Data Index: 932300 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6517. Min Act: -0.0000

Data Index: 53398 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5931. Min Act: -0.0000

Data Index: 934262 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6007. Min Act: -0.0000

Data Index: 813982 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1327951 (C4 (Web Text))

Max Activating Token Index: 992