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

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

Neuron 3840 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: 1.1071. Min Range: -1.1071

Max Act: 1.1071. Min Act: -0.0002

Data Index: 1196740 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 1.1071. Min Range: -1.1071

Max Act: 1.0801. Min Act: -0.0002

Data Index: 199508 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 1.1071. Min Range: -1.1071

Max Act: 1.1028. Min Act: -0.0002

Data Index: 258241 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 1.1071. Min Range: -1.1071

Max Act: 1.0707. Min Act: -0.0002

Data Index: 613465 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 1.1071. Min Range: -1.1071

Max Act: 1.0373. Min Act: -0.0002

Data Index: 2689 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 1.1071. Min Range: -1.1071

Max Act: 1.0049. Min Act: -0.0002

Data Index: 1214251 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9828. Min Act: -0.0002

Data Index: 14200 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9638. Min Act: -0.0002

Data Index: 744652 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9689. Min Act: -0.0002

Data Index: 327233 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9362. Min Act: -0.0002

Data Index: 751491 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9221. Min Act: -0.0002

Data Index: 405247 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9194. Min Act: -0.0002

Data Index: 1167705 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9314. Min Act: -0.0002

Data Index: 1123630 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9184. Min Act: -0.0002

Data Index: 30451 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9370. Min Act: -0.0002

Data Index: 480034 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8772. Min Act: -0.0002

Data Index: 622825 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8892. Min Act: -0.0002

Data Index: 528960 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8910. Min Act: -0.0002

Data Index: 644124 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8913. Min Act: -0.0002

Data Index: 412283 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9018. Min Act: -0.0002

Data Index: 66396 (C4 (Web Text))

Max Activating Token Index: 732