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

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

Neuron 288 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: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: -0.0003

Data Index: 654154 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1648328 (Python Code)

Max Activating Token Index: 948

Text #2

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0508. Min Act: -0.0003

Data Index: 107218 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1382476 (Python Code)

Max Activating Token Index: 535

Text #4

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1523569 (Python Code)

Max Activating Token Index: 435

Text #5

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0483. Min Act: -0.0002

Data Index: 56625 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1638428 (Python Code)

Max Activating Token Index: 720

Text #7

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0493. Min Act: -0.0003

Data Index: 884964 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1486390 (Python Code)

Max Activating Token Index: 349

Text #9

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0459. Min Act: -0.0003

Data Index: 61186 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1594138 (Python Code)

Max Activating Token Index: 514

Text #11

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0453. Min Act: -0.0003

Data Index: 6836 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1583082 (Python Code)

Max Activating Token Index: 938

Text #13

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1415462 (Python Code)

Max Activating Token Index: 685

Text #14

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0454. Min Act: -0.0003

Data Index: 980038 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1577367 (Python Code)

Max Activating Token Index: 499

Text #16

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1378323 (Python Code)

Max Activating Token Index: 270

Text #17

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1490317 (Python Code)

Max Activating Token Index: 973

Text #18

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0436. Min Act: -0.0003

Data Index: 423480 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0443. Min Act: -0.0003

Data Index: 1551558 (Python Code)

Max Activating Token Index: 733