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

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

Neuron 2714 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0815. Min Act: -0.0002

Data Index: 602534 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0737. Min Act: -0.0002

Data Index: 956351 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0647. Min Act: -0.0002

Data Index: 456979 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0620. Min Act: -0.0002

Data Index: 703783 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0657. Min Act: -0.0002

Data Index: 348158 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0636. Min Act: -0.0002

Data Index: 396841 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1169051 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0544. Min Act: -0.0002

Data Index: 430257 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0606. Min Act: -0.0002

Data Index: 939089 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0578. Min Act: -0.0002

Data Index: 800385 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0535. Min Act: -0.0002

Data Index: 392195 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0595. Min Act: -0.0002

Data Index: 839971 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0530. Min Act: -0.0002

Data Index: 481807 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0503. Min Act: -0.0003

Data Index: 590121 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0541. Min Act: -0.0002

Data Index: 150473 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1024268 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0543. Min Act: -0.0002

Data Index: 492052 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1308732 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1021945 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0489. Min Act: -0.0002

Data Index: 707427 (C4 (Web Text))

Max Activating Token Index: 800