Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 998 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0003

Data Index: 446383 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0004

Data Index: 528058 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0003

Data Index: 390221 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0003

Data Index: 730522 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1199997 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0130. Min Act: -0.0003

Data Index: 647851 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0129. Min Act: -0.0004

Data Index: 117449 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0129. Min Act: -0.0003

Data Index: 948220 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0128. Min Act: -0.0003

Data Index: 35846 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0124. Min Act: -0.0003

Data Index: 3027 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0126. Min Act: -0.0004

Data Index: 502137 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1319154 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0003

Data Index: 734043 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0123. Min Act: -0.0003

Data Index: 963445 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0123. Min Act: -0.0003

Data Index: 789635 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0123. Min Act: -0.0003

Data Index: 285047 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1294905 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0120. Min Act: -0.0004

Data Index: 473095 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0120. Min Act: -0.0003

Data Index: 881247 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0117. Min Act: -0.0003

Data Index: 715656 (C4 (Web Text))

Max Activating Token Index: 826