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

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

Neuron 4475 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1480. Min Act: -0.0002

Data Index: 1343860 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1141. Min Act: -0.0001

Data Index: 771151 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1115. Min Act: -0.0001

Data Index: 106784 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1112479 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0979. Min Act: -0.0002

Data Index: 165081 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1052. Min Act: -0.0002

Data Index: 22067 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0979. Min Act: -0.0001

Data Index: 956463 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1050. Min Act: -0.0002

Data Index: 536496 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0999. Min Act: -0.0002

Data Index: 361675 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1064. Min Act: -0.0002

Data Index: 668374 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0939. Min Act: -0.0002

Data Index: 357985 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0921. Min Act: -0.0002

Data Index: 569751 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0910. Min Act: -0.0002

Data Index: 49309 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1051469 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1089050 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0906. Min Act: -0.0002

Data Index: 413254 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0870. Min Act: -0.0002

Data Index: 499992 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1248956 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0819. Min Act: -0.0002

Data Index: 576659 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0851. Min Act: -0.0002

Data Index: 803294 (C4 (Web Text))

Max Activating Token Index: 908