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

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

Neuron 4941 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1144775 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0677. Min Act: -0.0002

Data Index: 256246 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0655. Min Act: -0.0002

Data Index: 935026 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0642. Min Act: -0.0002

Data Index: 390101 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0633. Min Act: -0.0002

Data Index: 919622 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0615. Min Act: -0.0002

Data Index: 921236 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0595. Min Act: -0.0002

Data Index: 227488 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0593. Min Act: -0.0002

Data Index: 791740 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0603. Min Act: -0.0002

Data Index: 242447 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1136493 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0568. Min Act: -0.0002

Data Index: 561833 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0556. Min Act: -0.0002

Data Index: 855687 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0585. Min Act: -0.0002

Data Index: 393357 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1189180 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0518. Min Act: -0.0002

Data Index: 125944 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0549. Min Act: -0.0002

Data Index: 578418 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0572. Min Act: -0.0002

Data Index: 183081 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0543. Min Act: -0.0002

Data Index: 960513 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0553. Min Act: -0.0002

Data Index: 997513 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0556. Min Act: -0.0002

Data Index: 669801 (C4 (Web Text))

Max Activating Token Index: 430