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

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

Neuron 3689 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1240425 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1327125 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0582. Min Act: -0.0003

Data Index: 144620 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0570. Min Act: -0.0002

Data Index: 509202 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1237507 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0492. Min Act: -0.0003

Data Index: 221553 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0502. Min Act: -0.0003

Data Index: 310907 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0490. Min Act: -0.0003

Data Index: 280766 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1300998 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0487. Min Act: -0.0003

Data Index: 416956 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0478. Min Act: -0.0002

Data Index: 656424 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0492. Min Act: -0.0002

Data Index: 623271 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0482. Min Act: -0.0003

Data Index: 566959 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0489. Min Act: -0.0003

Data Index: 649600 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1092179 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0460. Min Act: -0.0003

Data Index: 404325 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0467. Min Act: -0.0003

Data Index: 956244 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0457. Min Act: -0.0003

Data Index: 12871 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0464. Min Act: -0.0003

Data Index: 230819 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0465. Min Act: -0.0003

Data Index: 416675 (C4 (Web Text))

Max Activating Token Index: 859