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

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

Neuron 5290 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0207. Min Range: -7.0207

Max Act: 7.0207. Min Act: -0.0000

Data Index: 535870 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 7.0207. Min Range: -7.0207

Max Act: 6.7569. Min Act: -0.0000

Data Index: 1304503 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 7.0207. Min Range: -7.0207

Max Act: 6.3076. Min Act: -0.0000

Data Index: 593572 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.9359. Min Act: -0.0000

Data Index: 66244 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.7673. Min Act: -0.0000

Data Index: 811986 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.9260. Min Act: -0.0000

Data Index: 94509 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.7901. Min Act: -0.0000

Data Index: 1261127 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.9303. Min Act: -0.0000

Data Index: 254696 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.4717. Min Act: -0.0000

Data Index: 1232362 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.1648. Min Act: -0.0000

Data Index: 504883 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.3052. Min Act: -0.0000

Data Index: 789596 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.5751. Min Act: -0.0000

Data Index: 628986 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.3383. Min Act: -0.0000

Data Index: 1187553 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.3182. Min Act: -0.0000

Data Index: 538407 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.2443. Min Act: -0.0000

Data Index: 857280 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.6098. Min Act: -0.0000

Data Index: 622663 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.1801. Min Act: -0.0000

Data Index: 125223 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.3516. Min Act: -0.0000

Data Index: 394905 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.1267. Min Act: -0.0000

Data Index: 723032 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 7.0207. Min Range: -7.0207

Max Act: 5.1115. Min Act: -0.0000

Data Index: 435298 (C4 (Web Text))

Max Activating Token Index: 537