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

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

Neuron 2018 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: 0.0654. Min Range: -0.0654

Max Act: 0.0654. Min Act: -0.0003

Data Index: 351985 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0628. Min Act: -0.0003

Data Index: 507040 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0615. Min Act: -0.0003

Data Index: 217102 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0597. Min Act: -0.0003

Data Index: 356822 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0606. Min Act: -0.0003

Data Index: 1086489 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0596. Min Act: -0.0003

Data Index: 65278 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0586. Min Act: -0.0003

Data Index: 1353457 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1017938 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0590. Min Act: -0.0003

Data Index: 924055 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0547. Min Act: -0.0003

Data Index: 477205 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0574. Min Act: -0.0003

Data Index: 71742 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0550. Min Act: -0.0003

Data Index: 63271 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0544. Min Act: -0.0003

Data Index: 1038459 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0514. Min Act: -0.0003

Data Index: 795278 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0515. Min Act: -0.0003

Data Index: 510069 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0532. Min Act: -0.0003

Data Index: 407394 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1347757 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0504. Min Act: -0.0003

Data Index: 192729 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0510. Min Act: -0.0003

Data Index: 775865 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0496. Min Act: -0.0003

Data Index: 617354 (C4 (Web Text))

Max Activating Token Index: 627