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

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

Neuron 3237 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: 1.2675. Min Range: -1.2675

Max Act: 1.2675. Min Act: -0.0002

Data Index: 1223921 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.2400. Min Act: -0.0002

Data Index: 1234301 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.1653. Min Act: -0.0002

Data Index: 1149920 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.1402. Min Act: -0.0002

Data Index: 418564 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.1193. Min Act: -0.0002

Data Index: 440752 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.0833. Min Act: -0.0002

Data Index: 834314 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.1062. Min Act: -0.0002

Data Index: 1168246 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.0653. Min Act: -0.0002

Data Index: 684191 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.0609. Min Act: -0.0002

Data Index: 672787 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.0489. Min Act: -0.0002

Data Index: 763722 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.0551. Min Act: -0.0002

Data Index: 815316 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.0115. Min Act: -0.0002

Data Index: 749617 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.0172. Min Act: -0.0002

Data Index: 1191684 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.0337. Min Act: -0.0002

Data Index: 1250657 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 1.2675. Min Range: -1.2675

Max Act: 1.0221. Min Act: -0.0002

Data Index: 1230947 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 1.2675. Min Range: -1.2675

Max Act: 0.9837. Min Act: -0.0002

Data Index: 1165924 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 1.2675. Min Range: -1.2675

Max Act: 0.9797. Min Act: -0.0002

Data Index: 579807 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 1.2675. Min Range: -1.2675

Max Act: 0.9716. Min Act: -0.0002

Data Index: 55782 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.2675. Min Range: -1.2675

Max Act: 0.9635. Min Act: -0.0002

Data Index: 149616 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 1.2675. Min Range: -1.2675

Max Act: 0.9546. Min Act: -0.0002

Data Index: 1101868 (C4 (Web Text))

Max Activating Token Index: 406