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

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

Neuron 3996 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0740. Min Act: -0.0001

Data Index: 473400 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0605. Min Act: -0.0001

Data Index: 43521 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0609. Min Act: -0.0001

Data Index: 875796 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0570. Min Act: -0.0001

Data Index: 998760 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1012688 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1052821 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0487. Min Act: -0.0001

Data Index: 151958 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1266415 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0495. Min Act: -0.0001

Data Index: 230378 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0512. Min Act: -0.0001

Data Index: 901116 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0493. Min Act: -0.0002

Data Index: 815046 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0503. Min Act: -0.0002

Data Index: 907920 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0514. Min Act: -0.0002

Data Index: 621565 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0510. Min Act: -0.0001

Data Index: 663945 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0503. Min Act: -0.0002

Data Index: 501595 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0417. Min Act: -0.0002

Data Index: 118746 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0503. Min Act: -0.0001

Data Index: 271790 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0498. Min Act: -0.0001

Data Index: 503741 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0460. Min Act: -0.0001

Data Index: 27954 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0482. Min Act: -0.0001

Data Index: 699784 (C4 (Web Text))

Max Activating Token Index: 851