Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2846 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.6690. Min Act: -0.0000

Data Index: 399688 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.6375. Min Act: -0.0000

Data Index: 653395 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5128. Min Act: -0.0001

Data Index: 815539 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5080. Min Act: -0.0000

Data Index: 381917 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5328. Min Act: -0.0000

Data Index: 470830 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5422. Min Act: -0.0000

Data Index: 267425 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4564. Min Act: -0.0000

Data Index: 403318 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4834. Min Act: -0.0000

Data Index: 859411 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5145. Min Act: -0.0001

Data Index: 742998 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4628. Min Act: -0.0001

Data Index: 1036442 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4646. Min Act: -0.0001

Data Index: 815490 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4613. Min Act: -0.0000

Data Index: 390290 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4562. Min Act: -0.0000

Data Index: 290134 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4672. Min Act: -0.0000

Data Index: 145747 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1020184 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4511. Min Act: -0.0000

Data Index: 280932 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4215. Min Act: -0.0000

Data Index: 886656 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1130365 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4343. Min Act: -0.0000

Data Index: 39988 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.4615. Min Act: -0.0000

Data Index: 599715 (C4 (Web Text))

Max Activating Token Index: 877