Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2520 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0896. Min Act: -0.0001

Data Index: 1030303 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0860. Min Act: -0.0001

Data Index: 872256 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0840. Min Act: -0.0001

Data Index: 670208 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0813. Min Act: -0.0001

Data Index: 866379 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0761. Min Act: -0.0001

Data Index: 372946 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1255381 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0743. Min Act: -0.0001

Data Index: 597656 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0717. Min Act: -0.0001

Data Index: 96768 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1176185 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1163705 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0661. Min Act: -0.0001

Data Index: 218237 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0671. Min Act: -0.0001

Data Index: 442836 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0650. Min Act: -0.0001

Data Index: 977809 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1282683 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0627. Min Act: -0.0001

Data Index: 85154 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0624. Min Act: -0.0001

Data Index: 883226 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0628. Min Act: -0.0001

Data Index: 259 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0611. Min Act: -0.0001

Data Index: 955309 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0640. Min Act: -0.0001

Data Index: 993224 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0588. Min Act: -0.0001

Data Index: 766527 (C4 (Web Text))

Max Activating Token Index: 913