Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1194 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9453. Min Range: -3.9453

Max Act: 3.9453. Min Act: -0.0001

Data Index: 708199 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 3.9453. Min Range: -3.9453

Max Act: 3.8351. Min Act: -0.0000

Data Index: 263831 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 3.9453. Min Range: -3.9453

Max Act: 3.7225. Min Act: -0.0001

Data Index: 1009662 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 3.9453. Min Range: -3.9453

Max Act: 3.1498. Min Act: -0.0001

Data Index: 442916 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 3.9453. Min Range: -3.9453

Max Act: 3.3282. Min Act: -0.0001

Data Index: 314131 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.9298. Min Act: -0.0000

Data Index: 1250392 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 3.9453. Min Range: -3.9453

Max Act: 3.0636. Min Act: -0.0001

Data Index: 1012279 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.5280. Min Act: -0.0001

Data Index: 658171 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 3.9453. Min Range: -3.9453

Max Act: 3.0421. Min Act: -0.0000

Data Index: 713402 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.6929. Min Act: -0.0000

Data Index: 448372 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.6434. Min Act: -0.0000

Data Index: 929738 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.8968. Min Act: -0.0000

Data Index: 1045365 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.9191. Min Act: -0.0000

Data Index: 441899 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.8521. Min Act: -0.0001

Data Index: 794995 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.7086. Min Act: -0.0000

Data Index: 1264190 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.7032. Min Act: -0.0000

Data Index: 146124 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.6837. Min Act: -0.0001

Data Index: 369331 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.5929. Min Act: -0.0000

Data Index: 895779 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.4566. Min Act: -0.0000

Data Index: 279364 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 3.9453. Min Range: -3.9453

Max Act: 2.4422. Min Act: -0.0001

Data Index: 1092297 (C4 (Web Text))

Max Activating Token Index: 464