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

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

Neuron 345 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: 1.1862. Min Range: -1.1862

Max Act: 1.1862. Min Act: -0.0001

Data Index: 900773 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 1.1862. Min Range: -1.1862

Max Act: 1.1553. Min Act: -0.0000

Data Index: 1194970 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 1.1862. Min Range: -1.1862

Max Act: 1.0683. Min Act: -0.0001

Data Index: 666011 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 1.1862. Min Range: -1.1862

Max Act: 1.0558. Min Act: -0.0001

Data Index: 677666 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 1.1862. Min Range: -1.1862

Max Act: 1.0185. Min Act: -0.0001

Data Index: 556878 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 1.1862. Min Range: -1.1862

Max Act: 1.0176. Min Act: -0.0001

Data Index: 1068771 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 1.1862. Min Range: -1.1862

Max Act: 1.0081. Min Act: -0.0001

Data Index: 36474 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 1.1862. Min Range: -1.1862

Max Act: 1.0343. Min Act: -0.0001

Data Index: 222199 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 1.1862. Min Range: -1.1862

Max Act: 0.9430. Min Act: -0.0000

Data Index: 728123 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 1.1862. Min Range: -1.1862

Max Act: 0.9359. Min Act: -0.0001

Data Index: 577967 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 1.1862. Min Range: -1.1862

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1194889 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.1862. Min Range: -1.1862

Max Act: 0.9766. Min Act: -0.0001

Data Index: 652848 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 1.1862. Min Range: -1.1862

Max Act: 1.0088. Min Act: -0.0000

Data Index: 371293 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 1.1862. Min Range: -1.1862

Max Act: 0.9463. Min Act: -0.0001

Data Index: 1369218 (Python Code)

Max Activating Token Index: 665

Text #14

Max Range: 1.1862. Min Range: -1.1862

Max Act: 0.9380. Min Act: -0.0001

Data Index: 568139 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.1862. Min Range: -1.1862

Max Act: 0.9612. Min Act: -0.0001

Data Index: 803432 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 1.1862. Min Range: -1.1862

Max Act: 0.9514. Min Act: -0.0001

Data Index: 361560 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.1862. Min Range: -1.1862

Max Act: 0.9105. Min Act: -0.0001

Data Index: 483380 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 1.1862. Min Range: -1.1862

Max Act: 0.9393. Min Act: -0.0001

Data Index: 1228392 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.1862. Min Range: -1.1862

Max Act: 0.9076. Min Act: -0.0001

Data Index: 521588 (C4 (Web Text))

Max Activating Token Index: 895