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

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

Neuron 1338 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0746. Min Range: -1.0746

Max Act: 1.0746. Min Act: -0.0000

Data Index: 735097 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 1.0746. Min Range: -1.0746

Max Act: 1.0046. Min Act: -0.0000

Data Index: 1148442 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.7497. Min Act: -0.0000

Data Index: 332118 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6882. Min Act: 0.0000

Data Index: 1415045 (Python Code)

Max Activating Token Index: 559

Text #4

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1399565 (Python Code)

Max Activating Token Index: 879

Text #5

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6035. Min Act: -0.0000

Data Index: 835444 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1158629 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6111. Min Act: -0.0000

Data Index: 923883 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6521. Min Act: -0.0000

Data Index: 415585 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.5562. Min Act: 0.0001

Data Index: 503710 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.5721. Min Act: 0.0001

Data Index: 114492 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1309331 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.5598. Min Act: 0.0001

Data Index: 746106 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.5446. Min Act: 0.0000

Data Index: 542143 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1176313 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1503658 (Python Code)

Max Activating Token Index: 366

Text #16

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1177322 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.5355. Min Act: -0.0000

Data Index: 221844 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.5189. Min Act: 0.0000

Data Index: 416474 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.5265. Min Act: 0.0000

Data Index: 213494 (C4 (Web Text))

Max Activating Token Index: 274