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

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

Neuron 1402 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: 2.9694. Min Range: -2.9694

Max Act: 2.9694. Min Act: -0.0002

Data Index: 51320 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.6769. Min Act: -0.0002

Data Index: 666970 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.3594. Min Act: -0.0003

Data Index: 50765 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.3978. Min Act: -0.0002

Data Index: 1183274 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.2644. Min Act: -0.0002

Data Index: 431766 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.2402. Min Act: -0.0002

Data Index: 887560 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.2781. Min Act: -0.0002

Data Index: 976592 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.2596. Min Act: -0.0002

Data Index: 608106 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.2342. Min Act: -0.0002

Data Index: 435580 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.2038. Min Act: -0.0002

Data Index: 235730 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.2301. Min Act: -0.0003

Data Index: 830781 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.2348. Min Act: -0.0002

Data Index: 1290721 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.2063. Min Act: -0.0003

Data Index: 479137 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.1521. Min Act: -0.0002

Data Index: 1355514 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.1901. Min Act: -0.0003

Data Index: 636763 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.1672. Min Act: -0.0002

Data Index: 1278995 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.1253. Min Act: -0.0002

Data Index: 1058906 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.1679. Min Act: -0.0002

Data Index: 784002 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.1380. Min Act: -0.0002

Data Index: 888744 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 2.9694. Min Range: -2.9694

Max Act: 2.0791. Min Act: -0.0002

Data Index: 1036219 (C4 (Web Text))

Max Activating Token Index: 951