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

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

Neuron 2035 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: 0.3918. Min Range: -0.3918

Max Act: 0.3918. Min Act: -0.0000

Data Index: 550782 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3756. Min Act: -0.0000

Data Index: 7443 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3538. Min Act: -0.0000

Data Index: 424166 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3481. Min Act: -0.0000

Data Index: 987589 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1251801 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1218496 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1193032 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3091. Min Act: -0.0000

Data Index: 176077 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2942. Min Act: -0.0000

Data Index: 813512 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2988. Min Act: -0.0000

Data Index: 661119 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3037. Min Act: -0.0000

Data Index: 599908 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2787. Min Act: -0.0000

Data Index: 55138 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3124. Min Act: -0.0000

Data Index: 647375 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1021127 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2930. Min Act: -0.0000

Data Index: 619633 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1285321 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2920. Min Act: -0.0000

Data Index: 220341 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2866. Min Act: -0.0000

Data Index: 823517 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2658. Min Act: -0.0000

Data Index: 230858 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2658. Min Act: -0.0000

Data Index: 233365 (C4 (Web Text))

Max Activating Token Index: 914