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

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

Neuron 3116 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0562. Min Act: -0.0002

Data Index: 653159 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1324240 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0523. Min Act: -0.0002

Data Index: 975789 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1254910 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0474. Min Act: -0.0002

Data Index: 931117 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1097322 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0460. Min Act: -0.0002

Data Index: 672615 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1016769 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1001031 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1514374 (Python Code)

Max Activating Token Index: 338

Text #10

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0443. Min Act: -0.0002

Data Index: 636282 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1099842 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0452. Min Act: -0.0002

Data Index: 139057 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0451. Min Act: -0.0002

Data Index: 352426 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0427. Min Act: -0.0002

Data Index: 164471 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0434. Min Act: -0.0002

Data Index: 278327 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0435. Min Act: -0.0002

Data Index: 329688 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1194329 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0439. Min Act: -0.0002

Data Index: 621382 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0428. Min Act: -0.0002

Data Index: 431602 (C4 (Web Text))

Max Activating Token Index: 17