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

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

Neuron 2349 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1164. Min Act: -0.0002

Data Index: 984684 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1085. Min Act: -0.0003

Data Index: 1197215 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1357646 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0964. Min Act: -0.0002

Data Index: 364650 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0909. Min Act: -0.0002

Data Index: 769943 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0926. Min Act: -0.0002

Data Index: 245061 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0923. Min Act: -0.0002

Data Index: 99408 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0860. Min Act: -0.0003

Data Index: 989436 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1197552 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0818. Min Act: -0.0002

Data Index: 419179 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0816. Min Act: -0.0002

Data Index: 970627 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0786. Min Act: -0.0003

Data Index: 18886 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0780. Min Act: -0.0002

Data Index: 471283 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0780. Min Act: -0.0002

Data Index: 716784 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0762. Min Act: -0.0002

Data Index: 257820 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0756. Min Act: -0.0002

Data Index: 943675 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0747. Min Act: -0.0002

Data Index: 897373 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0730. Min Act: -0.0003

Data Index: 437790 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1164016 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0722. Min Act: -0.0003

Data Index: 218093 (C4 (Web Text))

Max Activating Token Index: 458