Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 838 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0005

Data Index: 52526 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0597. Min Act: -0.0005

Data Index: 672665 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0586. Min Act: -0.0005

Data Index: 837747 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0552. Min Act: -0.0005

Data Index: 439213 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0604. Min Act: -0.0005

Data Index: 480984 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0563. Min Act: -0.0005

Data Index: 1330415 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0553. Min Act: -0.0005

Data Index: 1258399 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0585. Min Act: -0.0005

Data Index: 645496 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0532. Min Act: -0.0005

Data Index: 733727 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0533. Min Act: -0.0005

Data Index: 849343 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0506. Min Act: -0.0005

Data Index: 918629 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0517. Min Act: -0.0005

Data Index: 1141455 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0523. Min Act: -0.0005

Data Index: 434360 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0545. Min Act: -0.0005

Data Index: 527243 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0523. Min Act: -0.0005

Data Index: 1307902 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0518. Min Act: -0.0005

Data Index: 255999 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0521. Min Act: -0.0005

Data Index: 930958 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0517. Min Act: -0.0005

Data Index: 601292 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0523. Min Act: -0.0005

Data Index: 341501 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0493. Min Act: -0.0005

Data Index: 1312200 (C4 (Web Text))

Max Activating Token Index: 597