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

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

Neuron 3026 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0635. Min Act: -0.0001

Data Index: 241454 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0558. Min Act: -0.0001

Data Index: 278797 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1327536 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1334887 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0574. Min Act: -0.0001

Data Index: 116280 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0540. Min Act: -0.0001

Data Index: 422806 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0578. Min Act: -0.0000

Data Index: 341640 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0554. Min Act: -0.0001

Data Index: 5493 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0523. Min Act: -0.0001

Data Index: 163862 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0519. Min Act: -0.0001

Data Index: 22111 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0543. Min Act: -0.0001

Data Index: 878385 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0582. Min Act: -0.0001

Data Index: 664090 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0557. Min Act: -0.0001

Data Index: 56957 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1448201 (Python Code)

Max Activating Token Index: 699

Text #14

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1269214 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0516. Min Act: -0.0001

Data Index: 646104 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1190519 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0512. Min Act: -0.0001

Data Index: 596773 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0499. Min Act: -0.0000

Data Index: 965349 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1011424 (C4 (Web Text))

Max Activating Token Index: 425