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

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

Neuron 4535 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.9773. Min Act: -0.0000

Data Index: 1174399 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 2.0120. Min Range: -2.0120

Max Act: 2.0120. Min Act: -0.0000

Data Index: 101531 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.7031. Min Act: -0.0000

Data Index: 111949 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.5452. Min Act: -0.0000

Data Index: 457588 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.4567. Min Act: -0.0000

Data Index: 1270623 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.4938. Min Act: -0.0000

Data Index: 372110 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.3947. Min Act: -0.0000

Data Index: 1168180 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.1534. Min Act: -0.0000

Data Index: 825127 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.1215. Min Act: -0.0000

Data Index: 451642 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.1931. Min Act: -0.0000

Data Index: 123051 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.1245. Min Act: -0.0000

Data Index: 92725 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.0549. Min Act: -0.0000

Data Index: 197980 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 2.0120. Min Range: -2.0120

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1266505 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1080303 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 2.0120. Min Range: -2.0120

Max Act: 0.9229. Min Act: -0.0000

Data Index: 730667 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 2.0120. Min Range: -2.0120

Max Act: 1.0572. Min Act: -0.0000

Data Index: 1084058 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 2.0120. Min Range: -2.0120

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1208670 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 2.0120. Min Range: -2.0120

Max Act: 0.9012. Min Act: -0.0000

Data Index: 428898 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 2.0120. Min Range: -2.0120

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1136409 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 2.0120. Min Range: -2.0120

Max Act: 0.9288. Min Act: -0.0000

Data Index: 872643 (C4 (Web Text))

Max Activating Token Index: 86