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

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

Neuron 5990 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1682. Min Act: -0.0000

Data Index: 745640 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1611. Min Act: -0.0001

Data Index: 1113960 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1085113 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1137132 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1367. Min Act: -0.0001

Data Index: 129927 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1236. Min Act: -0.0000

Data Index: 227006 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1268. Min Act: -0.0000

Data Index: 353568 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1642589 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1167. Min Act: -0.0000

Data Index: 944902 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1298. Min Act: -0.0001

Data Index: 906948 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1206. Min Act: -0.0001

Data Index: 374610 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1087100 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1228105 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1057. Min Act: -0.0001

Data Index: 194468 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1167. Min Act: -0.0000

Data Index: 591531 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1182530 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1203. Min Act: -0.0000

Data Index: 209096 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1093. Min Act: -0.0000

Data Index: 88309 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1602980 (Python Code)

Max Activating Token Index: 651

Text #19

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1090. Min Act: -0.0000

Data Index: 196514 (C4 (Web Text))

Max Activating Token Index: 173