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

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

Neuron 4314 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.8317. Min Act: -0.0000

Data Index: 1255325 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.8550. Min Act: -0.0000

Data Index: 504450 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.5949. Min Act: -0.0000

Data Index: 201263 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.5596. Min Act: -0.0000

Data Index: 635854 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.5506. Min Act: -0.0000

Data Index: 153330 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.4538. Min Act: -0.0000

Data Index: 37311 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.5048. Min Act: -0.0000

Data Index: 1081588 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.4754. Min Act: 0.0000

Data Index: 8709 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.4384. Min Act: 0.0000

Data Index: 1327773 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.4235. Min Act: -0.0000

Data Index: 292672 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.4000. Min Act: -0.0000

Data Index: 723303 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.4545. Min Act: -0.0000

Data Index: 668868 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.3521. Min Act: -0.0000

Data Index: 272857 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.4281. Min Act: -0.0000

Data Index: 591986 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.3818. Min Act: -0.0000

Data Index: 508717 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.3055. Min Act: -0.0000

Data Index: 800051 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.2093. Min Act: -0.0000

Data Index: 324516 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.2596. Min Act: -0.0000

Data Index: 499837 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.2581. Min Act: -0.0000

Data Index: 1341909 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 1.8550. Min Range: -1.8550

Max Act: 1.2300. Min Act: 0.0000

Data Index: 432027 (C4 (Web Text))

Max Activating Token Index: 935