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

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

Neuron 4034 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1283. Min Range: -5.1283

Max Act: 5.1283. Min Act: -0.0000

Data Index: 1080965 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.4883. Min Act: -0.0000

Data Index: 923458 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.5406. Min Act: -0.0000

Data Index: 74422 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.3104. Min Act: -0.0000

Data Index: 796623 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.4445. Min Act: -0.0000

Data Index: 1314350 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.0438. Min Act: -0.0000

Data Index: 226708 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.0862. Min Act: -0.0000

Data Index: 112528 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 5.1283. Min Range: -5.1283

Max Act: 3.8454. Min Act: -0.0000

Data Index: 1072886 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 5.1283. Min Range: -5.1283

Max Act: 3.6933. Min Act: -0.0000

Data Index: 1174875 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.0039. Min Act: -0.0000

Data Index: 642088 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.0350. Min Act: -0.0000

Data Index: 477600 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 5.1283. Min Range: -5.1283

Max Act: 3.7805. Min Act: -0.0000

Data Index: 1167173 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 5.1283. Min Range: -5.1283

Max Act: 3.9305. Min Act: -0.0000

Data Index: 1102909 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.4255. Min Act: -0.0000

Data Index: 806587 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.0883. Min Act: -0.0000

Data Index: 473098 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 5.1283. Min Range: -5.1283

Max Act: 3.7016. Min Act: -0.0000

Data Index: 1163462 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 5.1283. Min Range: -5.1283

Max Act: 3.9420. Min Act: -0.0000

Data Index: 1018893 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.2532. Min Act: -0.0000

Data Index: 955170 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 5.1283. Min Range: -5.1283

Max Act: 3.8987. Min Act: -0.0000

Data Index: 178452 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 5.1283. Min Range: -5.1283

Max Act: 3.8966. Min Act: -0.0000

Data Index: 1101717 (C4 (Web Text))

Max Activating Token Index: 495