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

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

Neuron 5578 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.6813. Min Act: -0.0000

Data Index: 116727 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.4725. Min Act: -0.0000

Data Index: 536325 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.4165. Min Act: -0.0000

Data Index: 970322 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.4482. Min Act: -0.0000

Data Index: 553848 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.3567. Min Act: -0.0000

Data Index: 1083447 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.4439. Min Act: -0.0000

Data Index: 112888 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.1064. Min Act: -0.0000

Data Index: 389765 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.5046. Min Act: -0.0000

Data Index: 780143 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.5060. Min Act: -0.0000

Data Index: 1311630 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.4191. Min Act: -0.0000

Data Index: 258593 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.2375. Min Act: -0.0000

Data Index: 309460 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.2910. Min Act: -0.0001

Data Index: 870572 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.3733. Min Act: -0.0000

Data Index: 998527 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.2252. Min Act: -0.0000

Data Index: 542386 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.2840. Min Act: -0.0000

Data Index: 836235 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.3427. Min Act: -0.0000

Data Index: 783001 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.3822. Min Act: -0.0000

Data Index: 190815 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.3347. Min Act: -0.0000

Data Index: 866888 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.2343. Min Act: -0.0000

Data Index: 616138 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 1.6813. Min Range: -1.6813

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1049708 (C4 (Web Text))

Max Activating Token Index: 560