Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 36 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1300806 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0921. Min Act: -0.0002

Data Index: 759089 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0844. Min Act: -0.0002

Data Index: 447201 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1214575 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1173082 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0789. Min Act: -0.0002

Data Index: 149328 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0770. Min Act: -0.0002

Data Index: 221974 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0771. Min Act: -0.0002

Data Index: 919399 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0751. Min Act: -0.0002

Data Index: 40079 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0681. Min Act: -0.0002

Data Index: 453901 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0713. Min Act: -0.0002

Data Index: 971445 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1287147 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1058126 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1341606 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1284818 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0670. Min Act: -0.0001

Data Index: 657008 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0644. Min Act: -0.0002

Data Index: 105550 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1356170 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1336634 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0643. Min Act: -0.0002

Data Index: 932887 (C4 (Web Text))

Max Activating Token Index: 634