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

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

Neuron 3158 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2352. Min Act: -0.0001

Data Index: 466522 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2129. Min Act: -0.0000

Data Index: 588553 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1827. Min Act: -0.0001

Data Index: 836080 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1293242 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1788. Min Act: -0.0001

Data Index: 364867 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1746. Min Act: -0.0001

Data Index: 804526 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1738. Min Act: -0.0001

Data Index: 578326 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1706. Min Act: -0.0001

Data Index: 908743 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1261002 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1517. Min Act: -0.0001

Data Index: 194269 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1423. Min Act: -0.0001

Data Index: 434423 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1317. Min Act: -0.0000

Data Index: 969821 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1286876 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1256. Min Act: -0.0000

Data Index: 81949 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1131. Min Act: -0.0001

Data Index: 931424 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1107240 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1143. Min Act: -0.0000

Data Index: 172867 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1350877 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1018. Min Act: -0.0001

Data Index: 35517 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1122. Min Act: -0.0001

Data Index: 612597 (C4 (Web Text))

Max Activating Token Index: 771