Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3421 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.4170. Min Act: -0.0000

Data Index: 292098 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1192355 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1251191 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2779. Min Act: -0.0000

Data Index: 801247 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1266262 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2752. Min Act: -0.0000

Data Index: 593596 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1181038 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2431. Min Act: -0.0000

Data Index: 285106 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2336. Min Act: -0.0000

Data Index: 704232 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2381. Min Act: -0.0000

Data Index: 445000 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2440. Min Act: -0.0000

Data Index: 744727 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2129. Min Act: -0.0000

Data Index: 167276 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1087063 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2160. Min Act: -0.0000

Data Index: 264133 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2075. Min Act: -0.0000

Data Index: 145755 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2037. Min Act: -0.0000

Data Index: 613056 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.1970. Min Act: -0.0000

Data Index: 495440 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2032. Min Act: -0.0000

Data Index: 354611 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.1783. Min Act: -0.0000

Data Index: 133889 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1359276 (C4 (Web Text))

Max Activating Token Index: 756