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

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

Neuron 4057 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1328. Min Act: -0.0000

Data Index: 573778 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1347. Min Act: -0.0000

Data Index: 393049 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1302. Min Act: -0.0000

Data Index: 238539 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1263. Min Act: -0.0000

Data Index: 845829 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1122. Min Act: -0.0000

Data Index: 626302 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1240. Min Act: -0.0000

Data Index: 336676 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1150. Min Act: -0.0000

Data Index: 617815 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1016. Min Act: -0.0000

Data Index: 323150 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1002. Min Act: -0.0000

Data Index: 185660 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1125290 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0969. Min Act: -0.0000

Data Index: 678601 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1093900 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1225390 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0977. Min Act: -0.0000

Data Index: 51003 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0952. Min Act: -0.0000

Data Index: 260930 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0973. Min Act: -0.0000

Data Index: 645119 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1010. Min Act: -0.0000

Data Index: 640607 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1306070 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1269481 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0876. Min Act: -0.0000

Data Index: 836717 (C4 (Web Text))

Max Activating Token Index: 143