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

Dataset: The Pile

Neuron 2444 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6605. Min Range: -3.6605

Max Act: 3.6605. Min Act: -0.0000

Data Index: 1513322 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 3.6605. Min Range: -3.6605

Max Act: 3.4901. Min Act: -0.0000

Data Index: 1689525 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 3.6605. Min Range: -3.6605

Max Act: 3.6310. Min Act: -0.0000

Data Index: 1971295 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 3.6605. Min Range: -3.6605

Max Act: 3.5266. Min Act: -0.0000

Data Index: 1653943 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 3.6605. Min Range: -3.6605

Max Act: 3.1572. Min Act: -0.0000

Data Index: 1473690 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 3.6605. Min Range: -3.6605

Max Act: 2.8447. Min Act: -0.0000

Data Index: 1782796 (The Pile)

Max Activating Token Index: 428

Text #6

Max Range: 3.6605. Min Range: -3.6605

Max Act: 3.1785. Min Act: -0.0000

Data Index: 1036145 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 3.6605. Min Range: -3.6605

Max Act: 3.0589. Min Act: -0.0000

Data Index: 472436 (The Pile)

Max Activating Token Index: 661

Text #8

Max Range: 3.6605. Min Range: -3.6605

Max Act: 3.1231. Min Act: -0.0000

Data Index: 216787 (The Pile)

Max Activating Token Index: 681

Text #9

Max Range: 3.6605. Min Range: -3.6605

Max Act: 2.8328. Min Act: -0.0000

Data Index: 691814 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 3.6605. Min Range: -3.6605

Max Act: 3.0007. Min Act: -0.0000

Data Index: 209802 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 3.6605. Min Range: -3.6605

Max Act: 2.6500. Min Act: -0.0000

Data Index: 3289 (The Pile)

Max Activating Token Index: 102

Text #12

Max Range: 3.6605. Min Range: -3.6605

Max Act: 2.8928. Min Act: -0.0000

Data Index: 289291 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 3.6605. Min Range: -3.6605

Max Act: 2.9380. Min Act: -0.0000

Data Index: 1378754 (The Pile)

Max Activating Token Index: 473

Text #14

Max Range: 3.6605. Min Range: -3.6605

Max Act: 2.8812. Min Act: -0.0000

Data Index: 133881 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 3.6605. Min Range: -3.6605

Max Act: 2.8759. Min Act: -0.0000

Data Index: 1173159 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 3.6605. Min Range: -3.6605

Max Act: 2.5390. Min Act: -0.0000

Data Index: 493662 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 3.6605. Min Range: -3.6605

Max Act: 2.6179. Min Act: -0.0000

Data Index: 642062 (The Pile)

Max Activating Token Index: 221

Text #18

Max Range: 3.6605. Min Range: -3.6605

Max Act: 2.4666. Min Act: -0.0000

Data Index: 679423 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 3.6605. Min Range: -3.6605

Max Act: 2.4271. Min Act: -0.0000

Data Index: 1754481 (The Pile)

Max Activating Token Index: 393