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

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

Neuron 2707 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0781. Min Range: -2.0781

Max Act: 2.0781. Min Act: 0.0001

Data Index: 1462046 (Python Code)

Max Activating Token Index: 253

Text #1

Max Range: 2.0781. Min Range: -2.0781

Max Act: 2.0371. Min Act: -0.0000

Data Index: 381150 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 2.0781. Min Range: -2.0781

Max Act: 1.4052. Min Act: -0.0000

Data Index: 118428 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 2.0781. Min Range: -2.0781

Max Act: 1.0442. Min Act: -0.0000

Data Index: 1164207 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 2.0781. Min Range: -2.0781

Max Act: 1.2033. Min Act: -0.0000

Data Index: 138441 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 2.0781. Min Range: -2.0781

Max Act: 1.1905. Min Act: -0.0000

Data Index: 593483 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 2.0781. Min Range: -2.0781

Max Act: 1.1857. Min Act: -0.0000

Data Index: 326327 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 2.0781. Min Range: -2.0781

Max Act: 1.0897. Min Act: -0.0000

Data Index: 979401 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 2.0781. Min Range: -2.0781

Max Act: 0.9457. Min Act: -0.0000

Data Index: 129649 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 2.0781. Min Range: -2.0781

Max Act: 0.9807. Min Act: -0.0000

Data Index: 496755 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 2.0781. Min Range: -2.0781

Max Act: 0.9968. Min Act: -0.0000

Data Index: 471335 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 2.0781. Min Range: -2.0781

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1251828 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 2.0781. Min Range: -2.0781

Max Act: 0.8810. Min Act: 0.0000

Data Index: 739398 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 2.0781. Min Range: -2.0781

Max Act: 0.9003. Min Act: -0.0000

Data Index: 841268 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 2.0781. Min Range: -2.0781

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1000180 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 2.0781. Min Range: -2.0781

Max Act: 0.8749. Min Act: -0.0000

Data Index: 581750 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 2.0781. Min Range: -2.0781

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1545422 (Python Code)

Max Activating Token Index: 603

Text #17

Max Range: 2.0781. Min Range: -2.0781

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1246489 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 2.0781. Min Range: -2.0781

Max Act: 0.8354. Min Act: -0.0000

Data Index: 539233 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 2.0781. Min Range: -2.0781

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1189200 (C4 (Web Text))

Max Activating Token Index: 235