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

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

Neuron 206 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: 0.0549. Min Range: -0.0549

Max Act: 0.0549. Min Act: -0.0003

Data Index: 639401 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0527. Min Act: -0.0002

Data Index: 248891 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0506. Min Act: -0.0002

Data Index: 590564 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0512. Min Act: -0.0003

Data Index: 205987 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0509. Min Act: -0.0003

Data Index: 574554 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0492. Min Act: -0.0003

Data Index: 856811 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1226873 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0510. Min Act: -0.0003

Data Index: 913479 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0470. Min Act: -0.0002

Data Index: 128030 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0481. Min Act: -0.0002

Data Index: 833742 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0469. Min Act: -0.0002

Data Index: 761426 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0452. Min Act: -0.0003

Data Index: 319608 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0465. Min Act: -0.0003

Data Index: 315126 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0466. Min Act: -0.0003

Data Index: 113613 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0463. Min Act: -0.0003

Data Index: 101427 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1196242 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0460. Min Act: -0.0003

Data Index: 979986 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0465. Min Act: -0.0002

Data Index: 114029 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0472. Min Act: -0.0003

Data Index: 799518 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0459. Min Act: -0.0002

Data Index: 822333 (C4 (Web Text))

Max Activating Token Index: 53