Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3340 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0193. Min Act: -0.0003

Data Index: 694614 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0141. Min Act: -0.0003

Data Index: 33645 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0146. Min Act: -0.0003

Data Index: 21966 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0139. Min Act: -0.0003

Data Index: 262589 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0144. Min Act: -0.0003

Data Index: 751276 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1163705 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0153. Min Act: -0.0003

Data Index: 673663 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0138. Min Act: -0.0003

Data Index: 1349288 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0140. Min Act: -0.0003

Data Index: 503016 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0138. Min Act: -0.0003

Data Index: 211262 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0140. Min Act: -0.0003

Data Index: 133508 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0138. Min Act: -0.0003

Data Index: 164501 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0132. Min Act: -0.0004

Data Index: 1237263 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0131. Min Act: -0.0003

Data Index: 308519 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1514767 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0131. Min Act: -0.0003

Data Index: 147597 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0125. Min Act: -0.0004

Data Index: 939102 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0145. Min Act: -0.0003

Data Index: 101333 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0117. Min Act: -0.0003

Data Index: 523394 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0123. Min Act: -0.0003

Data Index: 677482 (C4 (Web Text))

Max Activating Token Index: 51