Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1336 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1267. Min Range: -2.1267

Max Act: 2.0524. Min Act: -0.0002

Data Index: 365097 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 2.1267. Min Range: -2.1267

Max Act: 2.1267. Min Act: -0.0002

Data Index: 342337 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 2.1267. Min Range: -2.1267

Max Act: 2.0453. Min Act: -0.0002

Data Index: 655387 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 2.1267. Min Range: -2.1267

Max Act: 2.0138. Min Act: -0.0002

Data Index: 468877 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.8222. Min Act: -0.0002

Data Index: 342478 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 2.1267. Min Range: -2.1267

Max Act: 2.0613. Min Act: -0.0002

Data Index: 1272167 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.9590. Min Act: -0.0002

Data Index: 1129910 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.7605. Min Act: -0.0002

Data Index: 712225 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.9755. Min Act: -0.0002

Data Index: 706634 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.8171. Min Act: -0.0002

Data Index: 600996 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.9147. Min Act: -0.0002

Data Index: 899542 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.9580. Min Act: -0.0002

Data Index: 631250 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6689. Min Act: -0.0002

Data Index: 1342023 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6458. Min Act: -0.0002

Data Index: 1237276 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.5510. Min Act: -0.0002

Data Index: 1277728 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.8180. Min Act: -0.0002

Data Index: 594427 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.7561. Min Act: -0.0002

Data Index: 1131648 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.7151. Min Act: -0.0002

Data Index: 1073077 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.7589. Min Act: -0.0002

Data Index: 528662 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6506. Min Act: -0.0002

Data Index: 1184325 (C4 (Web Text))

Max Activating Token Index: 250