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

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

Neuron 1737 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.7449. Min Act: -0.0000

Data Index: 29346 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.7541. Min Act: -0.0000

Data Index: 501846 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6516. Min Act: -0.0000

Data Index: 269997 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6466. Min Act: -0.0000

Data Index: 99635 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6112. Min Act: -0.0000

Data Index: 424902 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5882. Min Act: -0.0000

Data Index: 323806 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5796. Min Act: -0.0000

Data Index: 67014 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5580. Min Act: -0.0000

Data Index: 764671 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1137423 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5287. Min Act: -0.0000

Data Index: 294765 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5222. Min Act: -0.0000

Data Index: 884442 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5401. Min Act: -0.0000

Data Index: 625349 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1057582 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5329. Min Act: -0.0000

Data Index: 551103 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5094. Min Act: -0.0000

Data Index: 298466 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1231060 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5046. Min Act: -0.0000

Data Index: 606651 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5035. Min Act: -0.0000

Data Index: 217877 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5180. Min Act: -0.0000

Data Index: 580576 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4682. Min Act: -0.0000

Data Index: 827258 (C4 (Web Text))

Max Activating Token Index: 273