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

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

Neuron 4112 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: 1.9896. Min Range: -1.9896

Max Act: 1.9383. Min Act: -0.0002

Data Index: 1154643 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9896. Min Act: -0.0002

Data Index: 644783 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.9012. Min Act: -0.0002

Data Index: 456220 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8542. Min Act: -0.0002

Data Index: 491742 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8654. Min Act: -0.0002

Data Index: 334449 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8142. Min Act: -0.0002

Data Index: 106306 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8033. Min Act: -0.0002

Data Index: 448836 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8048. Min Act: -0.0002

Data Index: 442482 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.8290. Min Act: -0.0002

Data Index: 968647 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.7802. Min Act: -0.0002

Data Index: 1252239 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.7599. Min Act: -0.0002

Data Index: 542409 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.7247. Min Act: -0.0002

Data Index: 419812 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.7755. Min Act: -0.0002

Data Index: 444374 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.7316. Min Act: -0.0002

Data Index: 766063 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.7187. Min Act: -0.0002

Data Index: 194791 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.7440. Min Act: -0.0002

Data Index: 689872 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.7074. Min Act: -0.0002

Data Index: 296636 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.7453. Min Act: -0.0002

Data Index: 334247 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.7294. Min Act: -0.0002

Data Index: 1189510 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 1.9896. Min Range: -1.9896

Max Act: 1.7378. Min Act: -0.0002

Data Index: 116935 (C4 (Web Text))

Max Activating Token Index: 369