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

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

Neuron 25 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: 0.0538. Min Range: -0.0538

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1497952 (Python Code)

Max Activating Token Index: 554

Text #1

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1550410 (Python Code)

Max Activating Token Index: 167

Text #2

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0538. Min Act: -0.0003

Data Index: 513266 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1080140 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1500301 (Python Code)

Max Activating Token Index: 531

Text #5

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1498694 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0498. Min Act: -0.0002

Data Index: 97836 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0453. Min Act: -0.0003

Data Index: 965258 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0496. Min Act: -0.0003

Data Index: 348695 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0498. Min Act: -0.0003

Data Index: 614441 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1466924 (Python Code)

Max Activating Token Index: 160

Text #11

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0478. Min Act: -0.0003

Data Index: 29361 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1631978 (Python Code)

Max Activating Token Index: 560

Text #13

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0363. Min Act: -0.0002

Data Index: 256941 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0497. Min Act: -0.0002

Data Index: 972929 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1576135 (Python Code)

Max Activating Token Index: 438

Text #16

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0377. Min Act: -0.0003

Data Index: 981390 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1360578 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1374861 (Python Code)

Max Activating Token Index: 424

Text #19

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0438. Min Act: -0.0003

Data Index: 855575 (C4 (Web Text))

Max Activating Token Index: 765