Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2694 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.9611. Min Act: -0.0001

Data Index: 1239922 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.4140. Min Act: -0.0001

Data Index: 1082821 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.4315. Min Act: -0.0001

Data Index: 123121 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.5520. Min Act: -0.0001

Data Index: 800135 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.9210. Min Act: -0.0001

Data Index: 969954 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.9134. Min Act: -0.0000

Data Index: 790349 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.4806. Min Act: -0.0001

Data Index: 1247439 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.0966. Min Act: -0.0001

Data Index: 398404 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.9661. Min Act: -0.0001

Data Index: 379512 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.0634. Min Act: -0.0001

Data Index: 188708 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.7382. Min Act: -0.0001

Data Index: 554640 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.5244. Min Act: -0.0001

Data Index: 1005009 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.3532. Min Act: -0.0001

Data Index: 997747 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.5689. Min Act: -0.0001

Data Index: 78271 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.3049. Min Act: -0.0000

Data Index: 1111549 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.6847. Min Act: -0.0001

Data Index: 1359667 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.5570. Min Act: -0.0001

Data Index: 554429 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.5911. Min Act: -0.0001

Data Index: 889320 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.3708. Min Act: -0.0001

Data Index: 468199 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 3.9611. Min Range: -3.9611

Max Act: 2.7319. Min Act: -0.0001

Data Index: 529292 (C4 (Web Text))

Max Activating Token Index: 17