Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1816 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2412. Min Act: -0.0001

Data Index: 1170915 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2316. Min Act: -0.0001

Data Index: 223109 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2298. Min Act: -0.0001

Data Index: 176735 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2251. Min Act: -0.0001

Data Index: 606288 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2222. Min Act: -0.0001

Data Index: 966945 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2194. Min Act: -0.0001

Data Index: 249026 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2213. Min Act: -0.0001

Data Index: 64314 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2135. Min Act: -0.0002

Data Index: 783057 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2145. Min Act: -0.0001

Data Index: 786930 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1006974 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2150. Min Act: -0.0001

Data Index: 204921 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2114. Min Act: -0.0001

Data Index: 492846 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2199. Min Act: -0.0001

Data Index: 449171 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2119. Min Act: -0.0001

Data Index: 1289698 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2104. Min Act: -0.0001

Data Index: 389458 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2091. Min Act: -0.0001

Data Index: 749948 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2084. Min Act: -0.0001

Data Index: 601366 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2116. Min Act: -0.0001

Data Index: 174233 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2049. Min Act: -0.0001

Data Index: 213229 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2057. Min Act: -0.0001

Data Index: 942469 (C4 (Web Text))

Max Activating Token Index: 701