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

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

Neuron 1304 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: 1.2030. Min Range: -1.2030

Max Act: 1.2030. Min Act: -0.0000

Data Index: 428775 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 1.2030. Min Range: -1.2030

Max Act: 1.1635. Min Act: -0.0000

Data Index: 1008598 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.2030. Min Range: -1.2030

Max Act: 1.1301. Min Act: -0.0000

Data Index: 497748 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9930. Min Act: -0.0000

Data Index: 862649 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 1.2030. Min Range: -1.2030

Max Act: 1.1393. Min Act: -0.0000

Data Index: 1090026 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 1.2030. Min Range: -1.2030

Max Act: 1.1039. Min Act: -0.0000

Data Index: 1274055 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 1.2030. Min Range: -1.2030

Max Act: 1.0301. Min Act: -0.0001

Data Index: 612990 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 1.2030. Min Range: -1.2030

Max Act: 1.1131. Min Act: -0.0001

Data Index: 654230 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9891. Min Act: -0.0001

Data Index: 372653 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9490. Min Act: -0.0001

Data Index: 901272 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9416. Min Act: -0.0001

Data Index: 507546 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9185. Min Act: -0.0001

Data Index: 1264486 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.8332. Min Act: -0.0001

Data Index: 951306 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9262. Min Act: -0.0001

Data Index: 172590 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.8733. Min Act: -0.0001

Data Index: 910993 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.7611. Min Act: -0.0001

Data Index: 526023 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.7294. Min Act: -0.0001

Data Index: 1072534 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.7804. Min Act: -0.0001

Data Index: 1066892 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.8541. Min Act: -0.0000

Data Index: 348534 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.6717. Min Act: -0.0000

Data Index: 958480 (C4 (Web Text))

Max Activating Token Index: 352