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

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

Neuron 4550 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5517. Min Range: -2.5517

Max Act: 2.5517. Min Act: -0.0000

Data Index: 279518 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 2.5517. Min Range: -2.5517

Max Act: 2.4968. Min Act: -0.0000

Data Index: 846361 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 2.5517. Min Range: -2.5517

Max Act: 2.2810. Min Act: -0.0000

Data Index: 441414 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 2.5517. Min Range: -2.5517

Max Act: 2.1770. Min Act: -0.0000

Data Index: 1224900 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 2.5517. Min Range: -2.5517

Max Act: 2.2553. Min Act: -0.0000

Data Index: 618374 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 2.5517. Min Range: -2.5517

Max Act: 2.1193. Min Act: -0.0000

Data Index: 816449 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.9678. Min Act: -0.0000

Data Index: 1138638 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.8473. Min Act: -0.0000

Data Index: 1015803 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.8833. Min Act: -0.0000

Data Index: 539333 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.8897. Min Act: -0.0000

Data Index: 743621 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.9773. Min Act: -0.0000

Data Index: 174096 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.8364. Min Act: -0.0000

Data Index: 667789 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.7619. Min Act: -0.0000

Data Index: 1001731 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.7593. Min Act: -0.0000

Data Index: 189118 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.7319. Min Act: -0.0000

Data Index: 58315 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.7307. Min Act: -0.0000

Data Index: 1232530 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.6994. Min Act: -0.0000

Data Index: 1068641 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.6150. Min Act: -0.0000

Data Index: 1040921 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.6901. Min Act: -0.0000

Data Index: 83282 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 2.5517. Min Range: -2.5517

Max Act: 1.6729. Min Act: -0.0000

Data Index: 958998 (C4 (Web Text))

Max Activating Token Index: 859