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

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

Neuron 3550 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4648. Min Range: -3.4648

Max Act: 3.4648. Min Act: -0.0000

Data Index: 321531 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 3.4648. Min Range: -3.4648

Max Act: 3.4194. Min Act: -0.0000

Data Index: 189043 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 3.4648. Min Range: -3.4648

Max Act: 3.1157. Min Act: -0.0000

Data Index: 960175 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 3.4648. Min Range: -3.4648

Max Act: 3.2189. Min Act: -0.0000

Data Index: 1258966 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 3.4648. Min Range: -3.4648

Max Act: 3.0103. Min Act: -0.0000

Data Index: 507459 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 3.4648. Min Range: -3.4648

Max Act: 3.0877. Min Act: -0.0000

Data Index: 978010 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 3.4648. Min Range: -3.4648

Max Act: 3.0064. Min Act: -0.0000

Data Index: 913366 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.8595. Min Act: -0.0000

Data Index: 361758 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.9580. Min Act: -0.0000

Data Index: 1066291 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.8137. Min Act: -0.0000

Data Index: 104511 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.8231. Min Act: -0.0000

Data Index: 305762 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.9775. Min Act: -0.0000

Data Index: 3157 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.9297. Min Act: -0.0000

Data Index: 43300 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.9080. Min Act: -0.0000

Data Index: 1180160 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.3199. Min Act: -0.0000

Data Index: 393917 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.9966. Min Act: -0.0000

Data Index: 435859 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.5503. Min Act: -0.0000

Data Index: 1081857 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.9761. Min Act: -0.0000

Data Index: 817307 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.4211. Min Act: -0.0000

Data Index: 1094831 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 3.4648. Min Range: -3.4648

Max Act: 2.5038. Min Act: -0.0000

Data Index: 323388 (C4 (Web Text))

Max Activating Token Index: 946