Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 308 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0172. Min Act: -0.0005

Data Index: 571194 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0167. Min Act: -0.0005

Data Index: 151104 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0162. Min Act: -0.0005

Data Index: 1329439 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0162. Min Act: -0.0005

Data Index: 263157 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0161. Min Act: -0.0005

Data Index: 744430 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0159. Min Act: -0.0005

Data Index: 1319128 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0156. Min Act: -0.0005

Data Index: 914679 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0153. Min Act: -0.0005

Data Index: 1144837 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0150. Min Act: -0.0005

Data Index: 267789 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0149. Min Act: -0.0005

Data Index: 899503 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0153. Min Act: -0.0005

Data Index: 930279 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0152. Min Act: -0.0006

Data Index: 663977 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0152. Min Act: -0.0005

Data Index: 1352390 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0148. Min Act: -0.0005

Data Index: 1347468 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0147. Min Act: -0.0005

Data Index: 948679 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0151. Min Act: -0.0005

Data Index: 587465 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1639539 (Python Code)

Max Activating Token Index: 1018

Text #17

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1306820 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0150. Min Act: -0.0005

Data Index: 916017 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0146. Min Act: -0.0005

Data Index: 1226715 (C4 (Web Text))

Max Activating Token Index: 324