Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1214 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.5047. Min Act: -0.0001

Data Index: 1311653 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4386. Min Act: -0.0001

Data Index: 588376 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4383. Min Act: -0.0001

Data Index: 396347 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4306. Min Act: -0.0001

Data Index: 1329197 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4173. Min Act: -0.0001

Data Index: 1302488 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4004. Min Act: -0.0001

Data Index: 761629 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4276. Min Act: -0.0001

Data Index: 674127 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3980. Min Act: -0.0001

Data Index: 1358521 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4249. Min Act: -0.0001

Data Index: 603665 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3961. Min Act: -0.0001

Data Index: 1208633 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4069. Min Act: -0.0001

Data Index: 571732 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4169. Min Act: -0.0001

Data Index: 94608 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4028. Min Act: -0.0001

Data Index: 253614 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3979. Min Act: -0.0001

Data Index: 1085011 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4109. Min Act: -0.0001

Data Index: 166782 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4021. Min Act: -0.0001

Data Index: 233705 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3991. Min Act: -0.0001

Data Index: 583723 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3678. Min Act: -0.0001

Data Index: 679814 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3780. Min Act: -0.0001

Data Index: 11323 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3752. Min Act: -0.0001

Data Index: 398550 (C4 (Web Text))

Max Activating Token Index: 984