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

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

Neuron 2621 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: 0.2263. Min Range: -0.2263

Max Act: 0.2263. Min Act: -0.0001

Data Index: 1249861 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2206. Min Act: -0.0000

Data Index: 117796 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2144. Min Act: -0.0000

Data Index: 407765 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2131. Min Act: -0.0001

Data Index: 80468 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2000. Min Act: -0.0001

Data Index: 513412 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1965. Min Act: -0.0001

Data Index: 767454 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1949. Min Act: -0.0000

Data Index: 7432 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1811. Min Act: -0.0000

Data Index: 509439 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1875. Min Act: -0.0001

Data Index: 516178 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1761. Min Act: -0.0000

Data Index: 82839 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1813. Min Act: -0.0001

Data Index: 117533 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1725. Min Act: -0.0000

Data Index: 911832 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1742. Min Act: -0.0000

Data Index: 53152 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1749. Min Act: -0.0001

Data Index: 1178575 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1731. Min Act: -0.0001

Data Index: 346266 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1703. Min Act: -0.0000

Data Index: 927438 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1211641 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1693. Min Act: -0.0000

Data Index: 329534 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1954. Min Act: -0.0000

Data Index: 379413 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1681. Min Act: -0.0000

Data Index: 716055 (C4 (Web Text))

Max Activating Token Index: 274