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

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

Neuron 5691 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.3911. Min Act: -0.0002

Data Index: 331078 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.2780. Min Act: -0.0002

Data Index: 663810 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.2623. Min Act: -0.0002

Data Index: 403736 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.2478. Min Act: -0.0002

Data Index: 406512 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.2357. Min Act: -0.0002

Data Index: 1245728 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.2227. Min Act: -0.0002

Data Index: 640329 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1929. Min Act: -0.0002

Data Index: 732111 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1882. Min Act: -0.0002

Data Index: 1359267 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1799. Min Act: -0.0002

Data Index: 1157451 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1705. Min Act: -0.0002

Data Index: 846421 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1834. Min Act: -0.0002

Data Index: 533887 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1736. Min Act: -0.0002

Data Index: 78216 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1663. Min Act: -0.0002

Data Index: 732075 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1402. Min Act: -0.0002

Data Index: 115835 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1459. Min Act: -0.0002

Data Index: 1134942 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1437. Min Act: -0.0002

Data Index: 866413 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1388. Min Act: -0.0002

Data Index: 691617 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1246. Min Act: -0.0002

Data Index: 1356277 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1306. Min Act: -0.0002

Data Index: 1029342 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1023. Min Act: -0.0002

Data Index: 210252 (C4 (Web Text))

Max Activating Token Index: 895