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

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

Neuron 2490 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1208. Min Range: -2.1208

Max Act: 2.1075. Min Act: -0.0000

Data Index: 166883 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 2.1208. Min Range: -2.1208

Max Act: 2.1208. Min Act: -0.0000

Data Index: 750848 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.9342. Min Act: -0.0000

Data Index: 874151 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.9108. Min Act: -0.0000

Data Index: 285747 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.8962. Min Act: -0.0000

Data Index: 598806 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.7691. Min Act: -0.0000

Data Index: 609891 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.8125. Min Act: -0.0000

Data Index: 1135337 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.6988. Min Act: -0.0000

Data Index: 215359 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.7689. Min Act: -0.0000

Data Index: 620573 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.7826. Min Act: -0.0000

Data Index: 736632 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5906. Min Act: -0.0000

Data Index: 466648 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5953. Min Act: -0.0000

Data Index: 318480 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5115. Min Act: -0.0000

Data Index: 494178 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5788. Min Act: -0.0000

Data Index: 333159 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5668. Min Act: -0.0000

Data Index: 563191 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5320. Min Act: -0.0000

Data Index: 789462 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5355. Min Act: -0.0000

Data Index: 1044473 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5238. Min Act: -0.0000

Data Index: 248410 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5093. Min Act: -0.0000

Data Index: 943994 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5159. Min Act: -0.0000

Data Index: 807340 (C4 (Web Text))

Max Activating Token Index: 110