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

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

Neuron 1519 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: 0.0553. Min Range: -0.0553

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1618633 (Python Code)

Max Activating Token Index: 712

Text #1

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1257543 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1533228 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1514435 (Python Code)

Max Activating Token Index: 446

Text #4

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1380744 (Python Code)

Max Activating Token Index: 468

Text #5

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1441138 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1642974 (Python Code)

Max Activating Token Index: 162

Text #7

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0505. Min Act: -0.0003

Data Index: 52012 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1639084 (Python Code)

Max Activating Token Index: 156

Text #9

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1570004 (Python Code)

Max Activating Token Index: 183

Text #10

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1548379 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1564134 (Python Code)

Max Activating Token Index: 399

Text #12

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0496. Min Act: -0.0003

Data Index: 385239 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1487564 (Python Code)

Max Activating Token Index: 158

Text #14

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1453864 (Python Code)

Max Activating Token Index: 285

Text #15

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0469. Min Act: -0.0004

Data Index: 38279 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1535926 (Python Code)

Max Activating Token Index: 267

Text #17

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1647770 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0470. Min Act: -0.0004

Data Index: 747770 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0451. Min Act: -0.0004

Data Index: 1069336 (C4 (Web Text))

Max Activating Token Index: 380