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

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

Neuron 1809 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.6179. Min Act: -0.0000

Data Index: 930071 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.5122. Min Act: -0.0001

Data Index: 577859 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.4635. Min Act: -0.0001

Data Index: 439043 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.3709. Min Act: -0.0001

Data Index: 1069210 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.4506. Min Act: -0.0001

Data Index: 941106 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.3585. Min Act: -0.0001

Data Index: 859964 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.3490. Min Act: -0.0001

Data Index: 1235399 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.4355. Min Act: -0.0001

Data Index: 672184 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.3931. Min Act: -0.0001

Data Index: 1206067 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.4187. Min Act: -0.0001

Data Index: 766139 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.3773. Min Act: -0.0001

Data Index: 72598 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.3690. Min Act: -0.0001

Data Index: 521030 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.3193. Min Act: -0.0001

Data Index: 33945 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.3738. Min Act: -0.0001

Data Index: 608184 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.3366. Min Act: -0.0001

Data Index: 1217927 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.3352. Min Act: -0.0001

Data Index: 401184 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.3566. Min Act: -0.0001

Data Index: 639998 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.3563. Min Act: -0.0001

Data Index: 502763 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.2612. Min Act: -0.0001

Data Index: 567934 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 1.6179. Min Range: -1.6179

Max Act: 1.2889. Min Act: -0.0001

Data Index: 1330362 (C4 (Web Text))

Max Activating Token Index: 608