Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3474 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.5748. Min Act: -0.0000

Data Index: 826350 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1347982 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.5462. Min Act: -0.0000

Data Index: 561207 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1233568 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.5368. Min Act: -0.0000

Data Index: 900671 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1267308 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4834. Min Act: -0.0000

Data Index: 598696 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4901. Min Act: -0.0000

Data Index: 455501 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4942. Min Act: -0.0000

Data Index: 844495 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4699. Min Act: -0.0000

Data Index: 844033 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4805. Min Act: -0.0000

Data Index: 969961 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4230. Min Act: -0.0000

Data Index: 272714 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4479. Min Act: -0.0000

Data Index: 872121 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4318. Min Act: -0.0000

Data Index: 803013 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4762. Min Act: -0.0000

Data Index: 160198 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4686. Min Act: -0.0000

Data Index: 684045 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4170. Min Act: -0.0000

Data Index: 391322 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4274. Min Act: -0.0000

Data Index: 613195 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4435. Min Act: -0.0000

Data Index: 512062 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4413. Min Act: -0.0000

Data Index: 617273 (C4 (Web Text))

Max Activating Token Index: 116