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

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

Neuron 5534 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2177. Min Act: -0.0000

Data Index: 815063 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1588 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2057. Min Act: -0.0000

Data Index: 245165 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2012. Min Act: 0.0001

Data Index: 433711 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1847. Min Act: 0.0004

Data Index: 995295 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1222878 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1893. Min Act: -0.0000

Data Index: 285943 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1814. Min Act: 0.0000

Data Index: 285489 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1746. Min Act: 0.0000

Data Index: 1254884 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1146723 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1613. Min Act: -0.0000

Data Index: 890990 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1067383 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1673. Min Act: 0.0001

Data Index: 1127468 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1235335 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1526. Min Act: -0.0000

Data Index: 502977 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1474. Min Act: 0.0000

Data Index: 806363 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1286493 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1473. Min Act: -0.0000

Data Index: 928130 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1575. Min Act: -0.0000

Data Index: 947834 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1497. Min Act: 0.0000

Data Index: 846861 (C4 (Web Text))

Max Activating Token Index: 492