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

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

Neuron 2014 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1472. Min Act: -0.0000

Data Index: 934413 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1346. Min Act: -0.0000

Data Index: 386201 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1357. Min Act: -0.0000

Data Index: 336044 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1022656 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1240. Min Act: -0.0000

Data Index: 41526 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1236822 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1231. Min Act: -0.0000

Data Index: 729217 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1127. Min Act: -0.0000

Data Index: 460378 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1159. Min Act: -0.0000

Data Index: 431755 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1183. Min Act: -0.0000

Data Index: 147484 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1121. Min Act: -0.0000

Data Index: 681347 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1343558 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1052524 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1040. Min Act: -0.0000

Data Index: 794866 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1004. Min Act: -0.0000

Data Index: 713332 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1124509 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1003. Min Act: -0.0000

Data Index: 48366 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0994. Min Act: -0.0000

Data Index: 89020 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1129. Min Act: -0.0000

Data Index: 940543 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1272574 (C4 (Web Text))

Max Activating Token Index: 492