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

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

Neuron 4529 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.5743. Min Act: -0.0001

Data Index: 1226132 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.5299. Min Act: -0.0001

Data Index: 100603 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4359. Min Act: -0.0001

Data Index: 561576 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4776. Min Act: -0.0001

Data Index: 389109 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4446. Min Act: -0.0001

Data Index: 1037515 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4403. Min Act: -0.0001

Data Index: 394893 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4120. Min Act: -0.0001

Data Index: 200365 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4033. Min Act: -0.0001

Data Index: 688017 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4021. Min Act: -0.0001

Data Index: 1228119 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4063. Min Act: -0.0001

Data Index: 1316329 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4091. Min Act: -0.0001

Data Index: 1271925 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3868. Min Act: -0.0001

Data Index: 603793 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3982. Min Act: -0.0001

Data Index: 484399 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1319351 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3624. Min Act: -0.0001

Data Index: 538585 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3818. Min Act: -0.0001

Data Index: 1102239 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3665. Min Act: -0.0001

Data Index: 1195314 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3770. Min Act: -0.0001

Data Index: 461892 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3794. Min Act: -0.0001

Data Index: 516551 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3764. Min Act: -0.0001

Data Index: 713951 (C4 (Web Text))

Max Activating Token Index: 3