Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 0 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1109872 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1245956 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0467. Min Act: -0.0003

Data Index: 550736 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0458. Min Act: -0.0003

Data Index: 506088 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0003

Data Index: 785888 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1630891 (Python Code)

Max Activating Token Index: 435

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0451. Min Act: -0.0003

Data Index: 236246 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1126211 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0432. Min Act: -0.0004

Data Index: 130612 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0430. Min Act: -0.0003

Data Index: 742002 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1075235 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0431. Min Act: -0.0003

Data Index: 337528 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1320111 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0408. Min Act: -0.0003

Data Index: 815433 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0414. Min Act: -0.0003

Data Index: 670681 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0415. Min Act: -0.0003

Data Index: 947720 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0421. Min Act: -0.0003

Data Index: 564180 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0415. Min Act: -0.0003

Data Index: 484698 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0425. Min Act: -0.0003

Data Index: 108838 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0403. Min Act: -0.0003

Data Index: 950352 (C4 (Web Text))

Max Activating Token Index: 627