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

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

Neuron 1003 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.8835. Min Act: -0.0001

Data Index: 866640 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.5138. Min Act: -0.0001

Data Index: 1077243 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.4146. Min Act: -0.0002

Data Index: 1331829 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.4148. Min Act: -0.0002

Data Index: 104594 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.2121. Min Act: -0.0002

Data Index: 601380 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.0253. Min Act: -0.0002

Data Index: 328222 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.1401. Min Act: -0.0001

Data Index: 807551 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.3997. Min Act: -0.0002

Data Index: 579347 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.9067. Min Act: -0.0001

Data Index: 419331 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.0225. Min Act: -0.0002

Data Index: 1217434 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.1300. Min Act: -0.0001

Data Index: 435886 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.8814. Min Act: -0.0002

Data Index: 261456 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.1143. Min Act: -0.0001

Data Index: 1204959 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.8598. Min Act: -0.0001

Data Index: 1018155 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.8367. Min Act: -0.0001

Data Index: 654773 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.4522. Min Act: -0.0001

Data Index: 385426 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.9570. Min Act: -0.0002

Data Index: 301300 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.9663. Min Act: -0.0001

Data Index: 1064953 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.4881. Min Act: -0.0001

Data Index: 807601 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.7981. Min Act: -0.0001

Data Index: 163199 (C4 (Web Text))

Max Activating Token Index: 569