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

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

Neuron 3100 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0254. Min Range: -1.0254

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1125248 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.7621. Min Act: -0.0000

Data Index: 483022 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.7155. Min Act: -0.0000

Data Index: 305881 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.7206. Min Act: -0.0000

Data Index: 959048 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.7101. Min Act: -0.0000

Data Index: 334239 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1073297 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1026984 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1190661 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1275073 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.7161. Min Act: -0.0000

Data Index: 578680 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1150028 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1349791 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.6189. Min Act: -0.0000

Data Index: 84916 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1247538 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.6042. Min Act: -0.0000

Data Index: 52463 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.5776. Min Act: -0.0000

Data Index: 749816 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.5671. Min Act: -0.0000

Data Index: 281494 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1141043 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1164479 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 1.0254. Min Range: -1.0254

Max Act: 0.5672. Min Act: -0.0000

Data Index: 705906 (C4 (Web Text))

Max Activating Token Index: 40