Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 982 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0152. Min Act: -0.0006

Data Index: 702998 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0143. Min Act: -0.0006

Data Index: 112509 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0147. Min Act: -0.0006

Data Index: 305983 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1345435 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1059838 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0145. Min Act: -0.0006

Data Index: 993465 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0135. Min Act: -0.0006

Data Index: 340441 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0137. Min Act: -0.0006

Data Index: 206261 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1193814 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1022289 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0126. Min Act: -0.0006

Data Index: 926675 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0128. Min Act: -0.0006

Data Index: 919217 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0127. Min Act: -0.0006

Data Index: 612027 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1349001 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1295550 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0123. Min Act: -0.0006

Data Index: 576121 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0129. Min Act: -0.0005

Data Index: 782258 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0125. Min Act: -0.0006

Data Index: 693425 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0131. Min Act: -0.0005

Data Index: 506695 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0122. Min Act: -0.0006

Data Index: 999811 (C4 (Web Text))

Max Activating Token Index: 846