Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2845 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0531. Min Act: -0.0003

Data Index: 314192 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0659. Min Act: -0.0003

Data Index: 100160 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0624. Min Act: -0.0003

Data Index: 265525 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0620. Min Act: -0.0003

Data Index: 150125 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0513. Min Act: -0.0003

Data Index: 336 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0609. Min Act: -0.0003

Data Index: 769558 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0581. Min Act: -0.0003

Data Index: 114828 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1243602 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0598. Min Act: -0.0003

Data Index: 447365 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1087885 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0491. Min Act: -0.0003

Data Index: 600439 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1238973 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0610. Min Act: -0.0003

Data Index: 141485 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0567. Min Act: -0.0003

Data Index: 694314 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0579. Min Act: -0.0003

Data Index: 958620 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0623. Min Act: -0.0003

Data Index: 410646 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0593. Min Act: -0.0003

Data Index: 53045 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0570. Min Act: -0.0003

Data Index: 126862 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0527. Min Act: -0.0003

Data Index: 431321 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0568. Min Act: -0.0003

Data Index: 59991 (C4 (Web Text))

Max Activating Token Index: 5