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

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

Neuron 2939 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0910. Min Act: -0.0002

Data Index: 353119 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0947. Min Act: -0.0002

Data Index: 554441 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0769. Min Act: -0.0002

Data Index: 303250 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0709. Min Act: -0.0002

Data Index: 24611 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0576. Min Act: -0.0002

Data Index: 623005 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1024264 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0568. Min Act: -0.0002

Data Index: 126560 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0532. Min Act: -0.0002

Data Index: 174017 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0459. Min Act: -0.0002

Data Index: 354149 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0424. Min Act: -0.0002

Data Index: 339477 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1133030 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0508. Min Act: -0.0002

Data Index: 616464 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0509. Min Act: -0.0002

Data Index: 496484 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0495. Min Act: -0.0002

Data Index: 896734 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0563. Min Act: -0.0002

Data Index: 375598 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0457. Min Act: -0.0002

Data Index: 788593 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0440. Min Act: -0.0002

Data Index: 244350 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0446. Min Act: -0.0002

Data Index: 511419 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0432. Min Act: -0.0002

Data Index: 806538 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1258673 (C4 (Web Text))

Max Activating Token Index: 332