Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3585 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.2761. Min Act: -0.0002

Data Index: 994192 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.2548. Min Act: -0.0002

Data Index: 1343446 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1693. Min Act: -0.0002

Data Index: 623664 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1925. Min Act: -0.0002

Data Index: 373763 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.2128. Min Act: -0.0002

Data Index: 294244 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.2011. Min Act: -0.0002

Data Index: 287103 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1633. Min Act: -0.0002

Data Index: 836260 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1562. Min Act: -0.0002

Data Index: 1014731 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1821. Min Act: -0.0002

Data Index: 1125524 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1600. Min Act: -0.0002

Data Index: 331615 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1866. Min Act: -0.0002

Data Index: 1267925 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1288. Min Act: -0.0002

Data Index: 1224329 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1503. Min Act: -0.0002

Data Index: 1002493 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1313. Min Act: -0.0002

Data Index: 1064172 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1548. Min Act: -0.0002

Data Index: 953493 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1140. Min Act: -0.0002

Data Index: 161984 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1107. Min Act: -0.0002

Data Index: 420025 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1337. Min Act: -0.0002

Data Index: 448076 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1111. Min Act: -0.0002

Data Index: 912982 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 1.2761. Min Range: -1.2761

Max Act: 1.1077. Min Act: -0.0002

Data Index: 369421 (C4 (Web Text))

Max Activating Token Index: 552