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

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

Neuron 4036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.3150. Min Act: -0.0000

Data Index: 156666 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2947. Min Act: -0.0001

Data Index: 1283484 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.3003. Min Act: -0.0000

Data Index: 357430 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2791. Min Act: -0.0001

Data Index: 248855 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2749. Min Act: -0.0001

Data Index: 795509 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2593. Min Act: -0.0001

Data Index: 439521 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2571. Min Act: -0.0000

Data Index: 367904 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2562. Min Act: -0.0001

Data Index: 186251 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2550. Min Act: -0.0001

Data Index: 272154 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2437. Min Act: -0.0001

Data Index: 363128 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2346. Min Act: -0.0001

Data Index: 2418 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2392. Min Act: -0.0001

Data Index: 1108742 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2373. Min Act: -0.0000

Data Index: 850544 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2300. Min Act: -0.0000

Data Index: 955037 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2357. Min Act: -0.0000

Data Index: 422352 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2184. Min Act: -0.0001

Data Index: 94142 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2208. Min Act: -0.0001

Data Index: 35311 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2128. Min Act: -0.0001

Data Index: 590596 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2252. Min Act: -0.0000

Data Index: 866327 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1002942 (C4 (Web Text))

Max Activating Token Index: 56