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

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

Neuron 2060 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.8146. Min Act: -0.0000

Data Index: 892715 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.7932. Min Act: -0.0000

Data Index: 911384 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.7842. Min Act: -0.0000

Data Index: 531655 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.7579. Min Act: -0.0000

Data Index: 28647 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1206806 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1324434 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.6909. Min Act: -0.0000

Data Index: 845993 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.6470. Min Act: -0.0000

Data Index: 644289 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1031777 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.6393. Min Act: -0.0000

Data Index: 381313 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.6591. Min Act: -0.0000

Data Index: 639577 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.6091. Min Act: -0.0000

Data Index: 467015 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1033667 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1022035 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.6380. Min Act: -0.0000

Data Index: 125547 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.5932. Min Act: -0.0000

Data Index: 813604 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.6051. Min Act: -0.0000

Data Index: 481478 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1054112 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.6094. Min Act: -0.0000

Data Index: 204663 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.6080. Min Act: -0.0000

Data Index: 672900 (C4 (Web Text))

Max Activating Token Index: 351