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

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

Neuron 2205 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.7971. Min Act: 0.0000

Data Index: 973075 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.7859. Min Act: 0.0001

Data Index: 1588112 (Python Code)

Max Activating Token Index: 391

Text #2

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.7536. Min Act: -0.0000

Data Index: 877187 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.7408. Min Act: -0.0000

Data Index: 287651 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.7281. Min Act: -0.0000

Data Index: 652046 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6772. Min Act: -0.0000

Data Index: 590361 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6390. Min Act: 0.0001

Data Index: 946735 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6716. Min Act: -0.0000

Data Index: 447084 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6683. Min Act: -0.0000

Data Index: 252715 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6423. Min Act: -0.0001

Data Index: 488898 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1316798 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6325. Min Act: -0.0000

Data Index: 477937 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6190. Min Act: -0.0000

Data Index: 104725 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6327. Min Act: 0.0000

Data Index: 994939 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6288. Min Act: 0.0001

Data Index: 448460 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6258. Min Act: -0.0000

Data Index: 362598 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.5962. Min Act: -0.0000

Data Index: 580450 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.5631. Min Act: -0.0000

Data Index: 710649 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.5763. Min Act: -0.0000

Data Index: 555406 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6022. Min Act: -0.0001

Data Index: 1382129 (Python Code)

Max Activating Token Index: 18