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

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

Neuron 4782 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1558. Min Range: -1.1558

Max Act: 1.1558. Min Act: -0.0002

Data Index: 788298 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 1.1558. Min Range: -1.1558

Max Act: 1.0179. Min Act: -0.0002

Data Index: 421548 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 1.1558. Min Range: -1.1558

Max Act: 1.0121. Min Act: -0.0002

Data Index: 916389 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.1558. Min Range: -1.1558

Max Act: 1.0325. Min Act: -0.0002

Data Index: 1118943 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 1.1558. Min Range: -1.1558

Max Act: 1.0142. Min Act: -0.0002

Data Index: 523036 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9669. Min Act: -0.0002

Data Index: 411632 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9775. Min Act: -0.0002

Data Index: 1627229 (Python Code)

Max Activating Token Index: 101

Text #7

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9771. Min Act: -0.0002

Data Index: 595517 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9566. Min Act: -0.0002

Data Index: 608341 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9211. Min Act: -0.0002

Data Index: 982613 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9686. Min Act: -0.0002

Data Index: 71431 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9366. Min Act: -0.0002

Data Index: 1045726 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.8934. Min Act: -0.0002

Data Index: 1264015 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9128. Min Act: -0.0002

Data Index: 556794 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9095. Min Act: -0.0002

Data Index: 1101116 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9109. Min Act: -0.0002

Data Index: 832073 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.8946. Min Act: -0.0002

Data Index: 1135808 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9131. Min Act: -0.0002

Data Index: 1238270 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.8941. Min Act: -0.0002

Data Index: 593812 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.8773. Min Act: -0.0002

Data Index: 1440588 (Python Code)

Max Activating Token Index: 558