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

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

Neuron 3374 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: 1.5851. Min Range: -1.5851

Max Act: 1.5851. Min Act: -0.0001

Data Index: 358488 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5733. Min Act: -0.0001

Data Index: 264940 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.3875. Min Act: -0.0001

Data Index: 948575 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.3959. Min Act: -0.0001

Data Index: 758212 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.3116. Min Act: -0.0001

Data Index: 1084466 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.2813. Min Act: -0.0001

Data Index: 467692 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.1858. Min Act: -0.0001

Data Index: 4060 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.1351. Min Act: -0.0001

Data Index: 637011 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.1736. Min Act: -0.0001

Data Index: 88864 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.1514. Min Act: -0.0001

Data Index: 1080590 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.1504. Min Act: -0.0001

Data Index: 537711 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0788. Min Act: -0.0001

Data Index: 1141250 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0709. Min Act: -0.0001

Data Index: 483192 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.1132. Min Act: -0.0001

Data Index: 525228 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0711. Min Act: -0.0001

Data Index: 779 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0665. Min Act: -0.0001

Data Index: 545389 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0358. Min Act: -0.0001

Data Index: 339859 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0727. Min Act: -0.0001

Data Index: 141252 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0299. Min Act: -0.0001

Data Index: 275828 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 1.5851. Min Range: -1.5851

Max Act: 0.9968. Min Act: -0.0001

Data Index: 281337 (C4 (Web Text))

Max Activating Token Index: 25