Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1335 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0716. Min Act: -0.0003

Data Index: 117709 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1298987 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0724. Min Act: -0.0003

Data Index: 814090 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1599690 (Python Code)

Max Activating Token Index: 549

Text #4

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0698. Min Act: -0.0003

Data Index: 327414 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0696. Min Act: -0.0003

Data Index: 78548 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0688. Min Act: -0.0003

Data Index: 366040 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1416677 (Python Code)

Max Activating Token Index: 917

Text #8

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0672. Min Act: -0.0003

Data Index: 818193 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1585182 (Python Code)

Max Activating Token Index: 393

Text #10

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0662. Min Act: -0.0003

Data Index: 413567 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0662. Min Act: -0.0003

Data Index: 787885 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0678. Min Act: -0.0003

Data Index: 182125 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1527921 (Python Code)

Max Activating Token Index: 449

Text #14

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0662. Min Act: -0.0003

Data Index: 343152 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0642. Min Act: -0.0003

Data Index: 760258 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0668. Min Act: -0.0003

Data Index: 130898 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1438656 (Python Code)

Max Activating Token Index: 307

Text #18

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0662. Min Act: -0.0003

Data Index: 311036 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1095542 (C4 (Web Text))

Max Activating Token Index: 649