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

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

Neuron 873 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0683. Min Act: -0.0001

Data Index: 103044 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1115715 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0617. Min Act: -0.0002

Data Index: 584675 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0564. Min Act: -0.0002

Data Index: 884877 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1648100 (Python Code)

Max Activating Token Index: 687

Text #5

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0485. Min Act: -0.0002

Data Index: 269743 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0509. Min Act: -0.0002

Data Index: 67857 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0484. Min Act: -0.0002

Data Index: 387268 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0443. Min Act: -0.0001

Data Index: 1047868 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0421. Min Act: -0.0001

Data Index: 779118 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0392. Min Act: -0.0001

Data Index: 583823 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1013794 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1279086 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0423. Min Act: -0.0002

Data Index: 625141 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1256147 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0401. Min Act: -0.0002

Data Index: 19249 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1320351 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1119534 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0370. Min Act: -0.0001

Data Index: 1190785 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1124108 (C4 (Web Text))

Max Activating Token Index: 198