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

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

Neuron 5620 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0756. Min Range: -2.0756

Max Act: 2.0756. Min Act: -0.0001

Data Index: 612615 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.8416. Min Act: -0.0001

Data Index: 892199 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.8108. Min Act: -0.0001

Data Index: 141363 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.9692. Min Act: -0.0001

Data Index: 630780 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.7661. Min Act: -0.0001

Data Index: 478494 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.8601. Min Act: -0.0001

Data Index: 1217503 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.8367. Min Act: -0.0000

Data Index: 47393 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.8022. Min Act: -0.0000

Data Index: 498535 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.7617. Min Act: -0.0000

Data Index: 569971 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.7487. Min Act: -0.0001

Data Index: 1358433 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.7620. Min Act: -0.0001

Data Index: 1156934 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.8370. Min Act: -0.0001

Data Index: 250658 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.7213. Min Act: -0.0000

Data Index: 504708 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.7109. Min Act: -0.0001

Data Index: 515991 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.8217. Min Act: -0.0000

Data Index: 251051 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.6005. Min Act: -0.0000

Data Index: 63979 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.8138. Min Act: -0.0000

Data Index: 1309180 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.7165. Min Act: -0.0000

Data Index: 488293 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.7410. Min Act: -0.0000

Data Index: 965005 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 2.0756. Min Range: -2.0756

Max Act: 1.5622. Min Act: -0.0000

Data Index: 58257 (C4 (Web Text))

Max Activating Token Index: 210