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

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

Neuron 6004 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.5823. Min Act: -0.0000

Data Index: 952925 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.5788. Min Act: -0.0000

Data Index: 811995 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.5314. Min Act: -0.0000

Data Index: 741093 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1145898 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1042918 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1358675 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4506. Min Act: -0.0000

Data Index: 391049 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1318584 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4092. Min Act: -0.0000

Data Index: 458263 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4297. Min Act: -0.0000

Data Index: 588272 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4025. Min Act: 0.0000

Data Index: 1019854 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4144. Min Act: -0.0000

Data Index: 782445 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1253454 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.3928. Min Act: -0.0000

Data Index: 754054 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.3846. Min Act: -0.0000

Data Index: 146554 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.3629. Min Act: -0.0000

Data Index: 876962 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1522481 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.3756. Min Act: -0.0000

Data Index: 937776 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.3622. Min Act: -0.0000

Data Index: 290540 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.3873. Min Act: -0.0000

Data Index: 766894 (C4 (Web Text))

Max Activating Token Index: 466