Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4783 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1876. Min Act: -0.0001

Data Index: 992402 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1509. Min Act: -0.0001

Data Index: 472487 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1549. Min Act: -0.0001

Data Index: 365547 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1226117 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1282. Min Act: -0.0001

Data Index: 513541 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1449. Min Act: -0.0001

Data Index: 446462 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1431. Min Act: -0.0001

Data Index: 624604 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1187159 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1334. Min Act: -0.0001

Data Index: 810361 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1158. Min Act: -0.0001

Data Index: 131437 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1318. Min Act: -0.0001

Data Index: 638623 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1283. Min Act: -0.0001

Data Index: 920480 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1327. Min Act: -0.0001

Data Index: 790151 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1330690 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1376. Min Act: -0.0001

Data Index: 397890 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1069970 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1206. Min Act: -0.0001

Data Index: 966590 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1148. Min Act: -0.0001

Data Index: 169064 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1259. Min Act: -0.0001

Data Index: 92263 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1107910 (C4 (Web Text))

Max Activating Token Index: 513