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

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

Neuron 2872 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: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0001

Data Index: 141330 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1573575 (Python Code)

Max Activating Token Index: 59

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1182246 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1086189 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0189. Min Act: -0.0001

Data Index: 806663 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0154. Min Act: -0.0001

Data Index: 1576952 (Python Code)

Max Activating Token Index: 757

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0162. Min Act: -0.0001

Data Index: 1360599 (Python Code)

Max Activating Token Index: 364

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1536275 (Python Code)

Max Activating Token Index: 73

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0173. Min Act: -0.0001

Data Index: 901440 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0158. Min Act: -0.0001

Data Index: 54098 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0143. Min Act: -0.0001

Data Index: 654386 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0134. Min Act: -0.0001

Data Index: 884522 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0149. Min Act: -0.0001

Data Index: 688944 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0139. Min Act: -0.0001

Data Index: 942520 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0133. Min Act: -0.0001

Data Index: 578297 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0140. Min Act: -0.0001

Data Index: 1582370 (Python Code)

Max Activating Token Index: 187

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0142. Min Act: -0.0001

Data Index: 1440765 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0128. Min Act: -0.0001

Data Index: 260112 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1442832 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0111. Min Act: -0.0001

Data Index: 465270 (C4 (Web Text))

Max Activating Token Index: 290