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

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

Neuron 2833 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0002

Data Index: 941680 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0657. Min Act: -0.0003

Data Index: 92319 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0636. Min Act: -0.0002

Data Index: 182861 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1175334 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0608. Min Act: -0.0003

Data Index: 137513 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0602. Min Act: -0.0002

Data Index: 679940 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0599. Min Act: -0.0003

Data Index: 446052 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0561. Min Act: -0.0003

Data Index: 891851 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0568. Min Act: -0.0002

Data Index: 287901 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0584. Min Act: -0.0002

Data Index: 380882 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0569. Min Act: -0.0002

Data Index: 233565 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0551. Min Act: -0.0003

Data Index: 833489 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1013857 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0572. Min Act: -0.0003

Data Index: 213833 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0532. Min Act: -0.0003

Data Index: 205851 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0532. Min Act: -0.0003

Data Index: 992585 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0498. Min Act: -0.0003

Data Index: 838515 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0510. Min Act: -0.0003

Data Index: 732009 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0510. Min Act: -0.0003

Data Index: 371289 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0519. Min Act: -0.0003

Data Index: 279628 (C4 (Web Text))

Max Activating Token Index: 844