Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 51 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1097232 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0155. Min Act: -0.0006

Data Index: 492330 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0147. Min Act: -0.0006

Data Index: 201296 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0149. Min Act: -0.0006

Data Index: 153519 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0139. Min Act: -0.0006

Data Index: 228810 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1196310 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0141. Min Act: -0.0006

Data Index: 42247 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1037593 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0144. Min Act: -0.0006

Data Index: 248544 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0134. Min Act: -0.0006

Data Index: 41304 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0137. Min Act: -0.0006

Data Index: 805310 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0140. Min Act: -0.0006

Data Index: 299764 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0139. Min Act: -0.0006

Data Index: 729308 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1633192 (Python Code)

Max Activating Token Index: 906

Text #14

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0129. Min Act: -0.0006

Data Index: 222362 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0138. Min Act: -0.0006

Data Index: 171171 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0131. Min Act: -0.0006

Data Index: 720724 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1105811 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0125. Min Act: -0.0006

Data Index: 644757 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0127. Min Act: -0.0006

Data Index: 670456 (C4 (Web Text))

Max Activating Token Index: 851