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

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

Neuron 4561 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: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0002

Data Index: 376221 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1055221 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0593. Min Act: -0.0002

Data Index: 568268 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1074482 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1115241 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0493. Min Act: -0.0002

Data Index: 526627 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0511. Min Act: -0.0002

Data Index: 438486 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0492. Min Act: -0.0002

Data Index: 794812 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1117559 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0468. Min Act: -0.0002

Data Index: 493189 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0454. Min Act: -0.0002

Data Index: 457647 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0468. Min Act: -0.0002

Data Index: 608566 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0449. Min Act: -0.0002

Data Index: 411896 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0450. Min Act: -0.0002

Data Index: 895194 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0450. Min Act: -0.0002

Data Index: 500680 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0456. Min Act: -0.0002

Data Index: 443612 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0426. Min Act: -0.0002

Data Index: 404284 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0421. Min Act: -0.0002

Data Index: 106533 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0432. Min Act: -0.0002

Data Index: 244653 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0432. Min Act: -0.0002

Data Index: 103920 (C4 (Web Text))

Max Activating Token Index: 574