Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3127 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1027836 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1135918 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0708. Min Act: -0.0002

Data Index: 546437 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0697. Min Act: -0.0002

Data Index: 463106 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1011209 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1339300 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1205044 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0711. Min Act: -0.0002

Data Index: 389309 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0696. Min Act: -0.0002

Data Index: 999322 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0693. Min Act: -0.0002

Data Index: 631960 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0661. Min Act: -0.0002

Data Index: 574420 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0617. Min Act: -0.0002

Data Index: 950061 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0565. Min Act: -0.0002

Data Index: 240484 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0585. Min Act: -0.0002

Data Index: 544238 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0624. Min Act: -0.0002

Data Index: 722361 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0587. Min Act: -0.0002

Data Index: 656849 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0582. Min Act: -0.0002

Data Index: 650984 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0572. Min Act: -0.0002

Data Index: 952611 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0569. Min Act: -0.0002

Data Index: 300063 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0540. Min Act: -0.0002

Data Index: 177755 (C4 (Web Text))

Max Activating Token Index: 112