Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3312 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.5685. Min Act: -0.0002

Data Index: 22136 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.5653. Min Act: -0.0002

Data Index: 1234810 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.4886. Min Act: -0.0002

Data Index: 1186078 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.5589. Min Act: -0.0002

Data Index: 1181457 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.5577. Min Act: -0.0002

Data Index: 1080326 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.4777. Min Act: -0.0002

Data Index: 1308779 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.5173. Min Act: -0.0002

Data Index: 181290 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.5088. Min Act: -0.0002

Data Index: 292299 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.4887. Min Act: -0.0002

Data Index: 831848 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.5314. Min Act: -0.0002

Data Index: 247478 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.5098. Min Act: -0.0002

Data Index: 1109673 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.5117. Min Act: -0.0001

Data Index: 19214 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.5281. Min Act: -0.0002

Data Index: 1046924 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.5029. Min Act: -0.0002

Data Index: 383153 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.5011. Min Act: -0.0002

Data Index: 286674 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.4857. Min Act: -0.0001

Data Index: 715213 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.4919. Min Act: -0.0002

Data Index: 530693 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.4977. Min Act: -0.0002

Data Index: 501575 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.4950. Min Act: -0.0002

Data Index: 1207264 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.5685. Min Range: -0.5685

Max Act: 0.4764. Min Act: -0.0002

Data Index: 192621 (C4 (Web Text))

Max Activating Token Index: 267