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

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

Neuron 475 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: 0.0606. Min Range: -0.0606

Max Act: 0.0606. Min Act: -0.0003

Data Index: 1048999 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0580. Min Act: -0.0003

Data Index: 139436 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0584. Min Act: -0.0002

Data Index: 815124 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0547. Min Act: -0.0003

Data Index: 568918 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0554. Min Act: -0.0003

Data Index: 879428 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0559. Min Act: -0.0003

Data Index: 115390 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1104689 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0532. Min Act: -0.0003

Data Index: 468995 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1136423 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0524. Min Act: -0.0003

Data Index: 447783 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0484. Min Act: -0.0002

Data Index: 101521 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0486. Min Act: -0.0004

Data Index: 382728 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0518. Min Act: -0.0003

Data Index: 411347 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0477. Min Act: -0.0003

Data Index: 921282 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0480. Min Act: -0.0003

Data Index: 239136 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0509. Min Act: -0.0003

Data Index: 859271 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1115656 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0474. Min Act: -0.0003

Data Index: 563048 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0468. Min Act: -0.0003

Data Index: 817987 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0488. Min Act: -0.0002

Data Index: 688982 (C4 (Web Text))

Max Activating Token Index: 56