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

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

Neuron 5830 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: 0.7109. Min Range: -0.7109

Max Act: 0.7109. Min Act: -0.0002

Data Index: 1278528 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6594. Min Act: -0.0002

Data Index: 105050 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6585. Min Act: -0.0002

Data Index: 437278 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6546. Min Act: -0.0002

Data Index: 628825 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6528. Min Act: -0.0002

Data Index: 1005139 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6322. Min Act: -0.0002

Data Index: 363811 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6396. Min Act: -0.0003

Data Index: 865828 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6386. Min Act: -0.0002

Data Index: 702263 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6277. Min Act: -0.0002

Data Index: 870497 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6271. Min Act: -0.0002

Data Index: 155024 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6166. Min Act: -0.0002

Data Index: 388976 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6284. Min Act: -0.0002

Data Index: 1288323 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6143. Min Act: -0.0002

Data Index: 743085 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6098. Min Act: -0.0002

Data Index: 1175566 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6273. Min Act: -0.0002

Data Index: 533957 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6071. Min Act: -0.0002

Data Index: 840199 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6249. Min Act: -0.0002

Data Index: 766135 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6076. Min Act: -0.0002

Data Index: 192068 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6159. Min Act: -0.0002

Data Index: 82181 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6049. Min Act: -0.0002

Data Index: 863427 (C4 (Web Text))

Max Activating Token Index: 403