Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1454 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0002

Data Index: 714729 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1603334 (Python Code)

Max Activating Token Index: 413

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1584162 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1137889 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1189455 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1514235 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1510205 (Python Code)

Max Activating Token Index: 917

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1387108 (Python Code)

Max Activating Token Index: 961

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1570647 (Python Code)

Max Activating Token Index: 561

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1175897 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0524. Min Act: -0.0002

Data Index: 239698 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1395083 (Python Code)

Max Activating Token Index: 220

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1283576 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1344641 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1016314 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1356874 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1362381 (Python Code)

Max Activating Token Index: 175

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0512. Min Act: -0.0002

Data Index: 710563 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1469321 (Python Code)

Max Activating Token Index: 711

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1496567 (Python Code)

Max Activating Token Index: 971