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

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

Neuron 2054 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1770. Min Range: -3.1770

Max Act: 3.1770. Min Act: -0.0000

Data Index: 880743 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.9460. Min Act: -0.0000

Data Index: 81068 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 3.1770. Min Range: -3.1770

Max Act: 3.0058. Min Act: -0.0000

Data Index: 896267 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.9920. Min Act: -0.0000

Data Index: 619634 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.7542. Min Act: -0.0000

Data Index: 1244472 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.4281. Min Act: -0.0000

Data Index: 763703 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.4419. Min Act: -0.0000

Data Index: 346437 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.5009. Min Act: -0.0000

Data Index: 1347574 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.1938. Min Act: -0.0000

Data Index: 1235089 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.1717. Min Act: -0.0000

Data Index: 248591 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.3530. Min Act: -0.0000

Data Index: 1251698 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.1580. Min Act: -0.0000

Data Index: 672253 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.0363. Min Act: -0.0000

Data Index: 226880 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.0149. Min Act: -0.0000

Data Index: 1020015 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.0117. Min Act: -0.0000

Data Index: 297212 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.1206. Min Act: -0.0000

Data Index: 1499478 (Python Code)

Max Activating Token Index: 487

Text #16

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.0617. Min Act: 0.0000

Data Index: 693306 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 3.1770. Min Range: -3.1770

Max Act: 1.9192. Min Act: -0.0000

Data Index: 473255 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.0216. Min Act: -0.0000

Data Index: 992220 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 3.1770. Min Range: -3.1770

Max Act: 2.0335. Min Act: -0.0000

Data Index: 1049835 (C4 (Web Text))

Max Activating Token Index: 819