Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2017 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1737. Min Act: -0.0003

Data Index: 1025783 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1548. Min Act: -0.0003

Data Index: 157517 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1524. Min Act: -0.0003

Data Index: 1022446 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1457. Min Act: -0.0003

Data Index: 126746 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1435. Min Act: -0.0003

Data Index: 247658 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1469. Min Act: -0.0003

Data Index: 243511 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1281. Min Act: -0.0003

Data Index: 664992 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1397. Min Act: -0.0003

Data Index: 681573 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1443. Min Act: -0.0003

Data Index: 431096 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1440. Min Act: -0.0003

Data Index: 167987 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1524. Min Act: -0.0003

Data Index: 1163505 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1450. Min Act: -0.0003

Data Index: 115717 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1447. Min Act: -0.0003

Data Index: 643509 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1380. Min Act: -0.0003

Data Index: 183788 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1341. Min Act: -0.0003

Data Index: 845708 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1332. Min Act: -0.0003

Data Index: 700402 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1463. Min Act: -0.0003

Data Index: 524175 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1256. Min Act: -0.0003

Data Index: 698551 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1450. Min Act: -0.0003

Data Index: 1148111 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1298. Min Act: -0.0003

Data Index: 17010 (C4 (Web Text))

Max Activating Token Index: 835