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

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

Neuron 2662 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.6821. Min Act: -0.0000

Data Index: 921877 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.6101. Min Act: 0.0000

Data Index: 101572 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5299. Min Act: -0.0000

Data Index: 55849 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5166. Min Act: -0.0000

Data Index: 89265 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5074. Min Act: -0.0000

Data Index: 885326 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1122897 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5031. Min Act: 0.0000

Data Index: 710823 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5044. Min Act: -0.0000

Data Index: 223123 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1156930 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5077. Min Act: -0.0000

Data Index: 222793 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4686. Min Act: 0.0001

Data Index: 421190 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4833. Min Act: -0.0000

Data Index: 406955 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4940. Min Act: -0.0000

Data Index: 238518 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4569. Min Act: -0.0000

Data Index: 386523 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4672. Min Act: 0.0000

Data Index: 321119 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4467. Min Act: -0.0000

Data Index: 308649 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4606. Min Act: -0.0000

Data Index: 604282 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4583. Min Act: 0.0001

Data Index: 1152420 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1156328 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1011790 (C4 (Web Text))

Max Activating Token Index: 57