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

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

Neuron 3767 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0676. Min Act: -0.0002

Data Index: 442423 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0669. Min Act: -0.0002

Data Index: 447361 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0644. Min Act: -0.0002

Data Index: 590359 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0668. Min Act: -0.0002

Data Index: 510200 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0654. Min Act: -0.0002

Data Index: 850308 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0665. Min Act: -0.0002

Data Index: 573603 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0658. Min Act: -0.0002

Data Index: 327258 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1156267 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1272148 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1070316 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0647. Min Act: -0.0002

Data Index: 521307 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0647. Min Act: -0.0002

Data Index: 387911 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1161505 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1330472 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0645. Min Act: -0.0002

Data Index: 242374 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0644. Min Act: -0.0002

Data Index: 160288 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1137478 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1215728 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0638. Min Act: -0.0002

Data Index: 489075 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0634. Min Act: -0.0002

Data Index: 157056 (C4 (Web Text))

Max Activating Token Index: 255