Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 102 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.4853. Min Act: -0.0000

Data Index: 135184 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.3759. Min Act: -0.0000

Data Index: 549306 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1037682 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.3132. Min Act: -0.0000

Data Index: 396011 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1318906 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.3353. Min Act: -0.0000

Data Index: 798506 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2841. Min Act: -0.0000

Data Index: 988916 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2780. Min Act: -0.0000

Data Index: 920120 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2452. Min Act: -0.0000

Data Index: 705558 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2679. Min Act: -0.0000

Data Index: 329953 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1229754 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2744. Min Act: -0.0000

Data Index: 502 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2805. Min Act: -0.0000

Data Index: 884326 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2356. Min Act: -0.0000

Data Index: 423548 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2433. Min Act: -0.0000

Data Index: 979732 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1332175 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2294. Min Act: -0.0000

Data Index: 202483 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2000. Min Act: -0.0000

Data Index: 102482 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2314. Min Act: -0.0000

Data Index: 612942 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.4853. Min Range: -0.4853

Max Act: 0.2125. Min Act: -0.0000

Data Index: 42540 (C4 (Web Text))

Max Activating Token Index: 457