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

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

Neuron 3642 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5895. Min Act: -0.0000

Data Index: 60845 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.6031. Min Act: -0.0000

Data Index: 303231 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5970. Min Act: -0.0000

Data Index: 386942 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5798. Min Act: -0.0000

Data Index: 214238 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5231. Min Act: -0.0000

Data Index: 952934 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1074153 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5607. Min Act: -0.0000

Data Index: 428540 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5263. Min Act: -0.0000

Data Index: 440342 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5353. Min Act: -0.0000

Data Index: 497023 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5144. Min Act: -0.0000

Data Index: 634737 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1212955 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5129. Min Act: -0.0000

Data Index: 216482 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4860. Min Act: -0.0000

Data Index: 159862 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4881. Min Act: -0.0000

Data Index: 801024 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4363. Min Act: -0.0000

Data Index: 955204 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4779. Min Act: -0.0000

Data Index: 943192 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4414. Min Act: -0.0000

Data Index: 519656 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4763. Min Act: -0.0000

Data Index: 727843 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4979. Min Act: -0.0000

Data Index: 707565 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4889. Min Act: -0.0000

Data Index: 192083 (C4 (Web Text))

Max Activating Token Index: 87