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

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

Neuron 2330 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2365. Min Act: -0.0000

Data Index: 89516 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2357. Min Act: -0.0001

Data Index: 720991 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2154. Min Act: -0.0001

Data Index: 143720 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2118. Min Act: -0.0001

Data Index: 61381 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2240. Min Act: -0.0000

Data Index: 114639 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1246935 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2122. Min Act: -0.0000

Data Index: 639667 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1911. Min Act: -0.0001

Data Index: 91686 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2064. Min Act: -0.0000

Data Index: 830233 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2078. Min Act: -0.0000

Data Index: 333024 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1314669 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1969. Min Act: -0.0001

Data Index: 228398 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2013. Min Act: -0.0001

Data Index: 532550 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1943. Min Act: -0.0000

Data Index: 474562 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1195717 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1887. Min Act: -0.0001

Data Index: 394298 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1860. Min Act: -0.0000

Data Index: 332453 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1857. Min Act: -0.0001

Data Index: 941855 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1919. Min Act: -0.0001

Data Index: 117196 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1910. Min Act: 0.0000

Data Index: 1256190 (C4 (Web Text))

Max Activating Token Index: 587