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

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

Neuron 955 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.9615. Min Act: -0.0000

Data Index: 995679 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 3.0666. Min Range: -3.0666

Max Act: 3.0666. Min Act: -0.0000

Data Index: 1335443 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.7427. Min Act: -0.0000

Data Index: 1331221 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.7386. Min Act: -0.0000

Data Index: 124844 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.7139. Min Act: -0.0000

Data Index: 733535 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.5666. Min Act: -0.0000

Data Index: 33754 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.6910. Min Act: -0.0000

Data Index: 1029345 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.6656. Min Act: -0.0000

Data Index: 97349 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.6770. Min Act: -0.0000

Data Index: 184959 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.7801. Min Act: -0.0000

Data Index: 1014701 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.6348. Min Act: -0.0000

Data Index: 171703 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.6337. Min Act: -0.0000

Data Index: 217422 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.6270. Min Act: -0.0000

Data Index: 540979 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.6163. Min Act: -0.0000

Data Index: 1150015 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.6110. Min Act: -0.0000

Data Index: 460293 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.6173. Min Act: -0.0000

Data Index: 90169 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.6104. Min Act: -0.0000

Data Index: 1109287 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.4803. Min Act: -0.0000

Data Index: 1130521 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.6188. Min Act: -0.0000

Data Index: 252323 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 3.0666. Min Range: -3.0666

Max Act: 2.6089. Min Act: -0.0000

Data Index: 658009 (C4 (Web Text))

Max Activating Token Index: 279