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

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

Neuron 2066 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: 0.0965. Min Range: -0.0965

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1205209 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0803. Min Act: -0.0002

Data Index: 126927 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0797. Min Act: -0.0002

Data Index: 669771 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0829. Min Act: -0.0002

Data Index: 502041 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0846. Min Act: -0.0002

Data Index: 284048 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0801. Min Act: -0.0002

Data Index: 424771 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0777. Min Act: -0.0002

Data Index: 374650 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0796. Min Act: -0.0002

Data Index: 80476 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0783. Min Act: -0.0002

Data Index: 632265 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0743. Min Act: -0.0002

Data Index: 896371 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0765. Min Act: -0.0002

Data Index: 220702 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0760. Min Act: -0.0002

Data Index: 390822 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1316761 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0761. Min Act: -0.0002

Data Index: 263395 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1268551 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0731. Min Act: -0.0002

Data Index: 377340 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1182534 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1322365 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0681. Min Act: -0.0002

Data Index: 206892 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1098629 (C4 (Web Text))

Max Activating Token Index: 278