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

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

Neuron 1437 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1637. Min Act: -0.0000

Data Index: 807759 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1369. Min Act: -0.0000

Data Index: 518389 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1220200 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1014493 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1242. Min Act: -0.0000

Data Index: 287351 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1229. Min Act: -0.0000

Data Index: 821476 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1220. Min Act: -0.0000

Data Index: 205835 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1100. Min Act: -0.0000

Data Index: 47051 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1125. Min Act: -0.0000

Data Index: 869209 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1146990 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1172. Min Act: -0.0000

Data Index: 998107 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1013. Min Act: -0.0000

Data Index: 435481 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1294684 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1184222 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1202163 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1049. Min Act: -0.0000

Data Index: 938475 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1050. Min Act: -0.0000

Data Index: 891668 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1257125 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1032. Min Act: -0.0000

Data Index: 90063 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.0970. Min Act: -0.0000

Data Index: 829619 (C4 (Web Text))

Max Activating Token Index: 234