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

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

Neuron 544 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.8085. Min Act: -0.0001

Data Index: 1271516 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7228. Min Act: -0.0001

Data Index: 1164894 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7154. Min Act: -0.0001

Data Index: 587439 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7324. Min Act: -0.0001

Data Index: 45250 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7240. Min Act: -0.0001

Data Index: 145491 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6844. Min Act: -0.0001

Data Index: 593067 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6894. Min Act: -0.0001

Data Index: 661720 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7003. Min Act: -0.0001

Data Index: 153204 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6736. Min Act: -0.0001

Data Index: 1061824 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6503. Min Act: -0.0001

Data Index: 892159 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6879. Min Act: -0.0001

Data Index: 612452 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6826. Min Act: -0.0001

Data Index: 891229 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6275. Min Act: -0.0001

Data Index: 84057 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6255. Min Act: -0.0001

Data Index: 321097 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6707. Min Act: -0.0001

Data Index: 434148 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6436. Min Act: -0.0001

Data Index: 965292 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6879. Min Act: -0.0001

Data Index: 673411 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6466. Min Act: -0.0001

Data Index: 72896 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6647. Min Act: -0.0001

Data Index: 675171 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6778. Min Act: -0.0001

Data Index: 48506 (C4 (Web Text))

Max Activating Token Index: 165