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

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

Neuron 1319 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: 0.0566. Min Range: -0.0566

Max Act: 0.0566. Min Act: -0.0005

Data Index: 84298 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0542. Min Act: -0.0005

Data Index: 758186 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0513. Min Act: -0.0005

Data Index: 47091 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0448. Min Act: -0.0005

Data Index: 1231446 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0492. Min Act: -0.0005

Data Index: 1341846 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0438. Min Act: -0.0005

Data Index: 21193 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0446. Min Act: -0.0005

Data Index: 800923 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0463. Min Act: -0.0005

Data Index: 894240 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0478. Min Act: -0.0005

Data Index: 1295797 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0485. Min Act: -0.0005

Data Index: 1183071 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0465. Min Act: -0.0005

Data Index: 665186 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0438. Min Act: -0.0005

Data Index: 659753 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0431. Min Act: -0.0005

Data Index: 1212682 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0442. Min Act: -0.0005

Data Index: 505784 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0432. Min Act: -0.0005

Data Index: 889446 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0421. Min Act: -0.0005

Data Index: 1047668 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0448. Min Act: -0.0005

Data Index: 1116016 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0429. Min Act: -0.0005

Data Index: 524868 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0431. Min Act: -0.0005

Data Index: 747626 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0422. Min Act: -0.0005

Data Index: 162851 (C4 (Web Text))

Max Activating Token Index: 410