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

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

Neuron 3929 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.9407. Min Act: -0.0001

Data Index: 137084 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.9699. Min Act: -0.0001

Data Index: 1219047 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.9627. Min Act: -0.0001

Data Index: 407614 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.9220. Min Act: -0.0001

Data Index: 651283 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.9691. Min Act: -0.0001

Data Index: 257470 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.9317. Min Act: -0.0001

Data Index: 390362 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8968. Min Act: -0.0001

Data Index: 696858 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8912. Min Act: -0.0001

Data Index: 1145720 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.9033. Min Act: -0.0001

Data Index: 53873 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8833. Min Act: -0.0000

Data Index: 9427 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.9105. Min Act: -0.0001

Data Index: 499698 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8507. Min Act: -0.0001

Data Index: 552057 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8738. Min Act: -0.0000

Data Index: 821223 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8915. Min Act: -0.0001

Data Index: 172097 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8644. Min Act: -0.0001

Data Index: 44396 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8906. Min Act: -0.0001

Data Index: 797852 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8541. Min Act: -0.0000

Data Index: 418845 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8566. Min Act: -0.0000

Data Index: 1281416 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8604. Min Act: -0.0000

Data Index: 305334 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1046193 (C4 (Web Text))

Max Activating Token Index: 676