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

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

Neuron 2133 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.4474. Min Act: -0.0002

Data Index: 1549584 (Python Code)

Max Activating Token Index: 895

Text #1

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.4451. Min Act: -0.0002

Data Index: 1479751 (Python Code)

Max Activating Token Index: 332

Text #2

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.4394. Min Act: -0.0002

Data Index: 1537007 (Python Code)

Max Activating Token Index: 794

Text #3

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.4263. Min Act: -0.0003

Data Index: 32840 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.4124. Min Act: -0.0003

Data Index: 1038456 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.4035. Min Act: -0.0002

Data Index: 1530013 (Python Code)

Max Activating Token Index: 298

Text #6

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3929. Min Act: -0.0003

Data Index: 146244 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3773. Min Act: -0.0003

Data Index: 1245740 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3601. Min Act: -0.0003

Data Index: 11476 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3720. Min Act: -0.0003

Data Index: 651757 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3671. Min Act: -0.0003

Data Index: 470234 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3548. Min Act: -0.0003

Data Index: 827155 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3546. Min Act: -0.0003

Data Index: 22948 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3475. Min Act: -0.0003

Data Index: 16172 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3467. Min Act: -0.0002

Data Index: 1545373 (Python Code)

Max Activating Token Index: 262

Text #15

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3338. Min Act: -0.0002

Data Index: 1388452 (Python Code)

Max Activating Token Index: 199

Text #16

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3442. Min Act: -0.0003

Data Index: 453237 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3437. Min Act: -0.0002

Data Index: 1516552 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3429. Min Act: -0.0002

Data Index: 1509414 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 0.4474. Min Range: -0.4474

Max Act: 0.3425. Min Act: -0.0002

Data Index: 1611172 (Python Code)

Max Activating Token Index: 812