Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2152 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.5534. Min Act: -0.0001

Data Index: 1171020 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4471. Min Act: -0.0001

Data Index: 1356663 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.5037. Min Act: -0.0001

Data Index: 1164851 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4114. Min Act: -0.0001

Data Index: 454690 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4532. Min Act: -0.0001

Data Index: 139358 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4563. Min Act: -0.0001

Data Index: 1156727 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4064. Min Act: -0.0001

Data Index: 275728 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4313. Min Act: -0.0001

Data Index: 815238 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4449. Min Act: -0.0001

Data Index: 622892 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4736. Min Act: -0.0001

Data Index: 192872 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4410. Min Act: -0.0001

Data Index: 265567 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4361. Min Act: -0.0001

Data Index: 702834 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4217. Min Act: -0.0001

Data Index: 669898 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4065. Min Act: -0.0001

Data Index: 152272 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4576. Min Act: -0.0001

Data Index: 1242984 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4421. Min Act: -0.0001

Data Index: 1137876 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4130. Min Act: -0.0001

Data Index: 1216531 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4201. Min Act: -0.0001

Data Index: 541842 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4058. Min Act: -0.0001

Data Index: 295262 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3537. Min Act: -0.0001

Data Index: 522000 (C4 (Web Text))

Max Activating Token Index: 556