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

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

Neuron 5939 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1034518 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7894. Min Act: -0.0000

Data Index: 579943 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7679. Min Act: -0.0000

Data Index: 952599 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7289. Min Act: -0.0000

Data Index: 965972 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7310. Min Act: -0.0000

Data Index: 140505 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6821. Min Act: -0.0000

Data Index: 273900 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1272062 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6616. Min Act: -0.0000

Data Index: 146137 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6207. Min Act: -0.0000

Data Index: 161453 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1059970 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1326034 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6660. Min Act: -0.0000

Data Index: 77244 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6307. Min Act: -0.0000

Data Index: 882406 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6226. Min Act: -0.0000

Data Index: 421467 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6168. Min Act: -0.0000

Data Index: 519655 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6588. Min Act: -0.0000

Data Index: 333724 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1323197 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6622. Min Act: -0.0000

Data Index: 808146 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6049. Min Act: -0.0000

Data Index: 268149 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1065311 (C4 (Web Text))

Max Activating Token Index: 987