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

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

Neuron 5354 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3229. Min Range: -6.3229

Max Act: 6.3229. Min Act: -0.0000

Data Index: 1132007 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 6.3229. Min Range: -6.3229

Max Act: 6.0261. Min Act: -0.0000

Data Index: 82885 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 6.3229. Min Range: -6.3229

Max Act: 6.0175. Min Act: -0.0000

Data Index: 562912 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.7910. Min Act: -0.0000

Data Index: 171216 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 6.3229. Min Range: -6.3229

Max Act: 6.2892. Min Act: -0.0001

Data Index: 958619 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.6245. Min Act: -0.0000

Data Index: 428050 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.9643. Min Act: -0.0000

Data Index: 924250 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.5435. Min Act: -0.0000

Data Index: 1353345 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.8889. Min Act: -0.0000

Data Index: 481121 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.3462. Min Act: -0.0000

Data Index: 119859 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.7007. Min Act: -0.0000

Data Index: 896719 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.7024. Min Act: -0.0000

Data Index: 467239 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.4989. Min Act: -0.0000

Data Index: 473588 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.6657. Min Act: -0.0000

Data Index: 465325 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.4917. Min Act: -0.0000

Data Index: 978891 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.1184. Min Act: -0.0000

Data Index: 707563 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.4619. Min Act: -0.0000

Data Index: 273551 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.5289. Min Act: -0.0000

Data Index: 17745 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.5328. Min Act: -0.0000

Data Index: 953241 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 6.3229. Min Range: -6.3229

Max Act: 5.1645. Min Act: -0.0000

Data Index: 1209378 (C4 (Web Text))

Max Activating Token Index: 855