Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 612 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0149. Min Act: -0.0000

Data Index: 1560019 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0140. Min Act: -0.0000

Data Index: 247395 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0138. Min Act: -0.0000

Data Index: 1509302 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0135. Min Act: -0.0000

Data Index: 310484 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0133. Min Act: -0.0000

Data Index: 1670969 (The Pile)

Max Activating Token Index: 686

Text #5

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0136. Min Act: -0.0000

Data Index: 355878 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0130. Min Act: -0.0000

Data Index: 1212348 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0133. Min Act: -0.0000

Data Index: 458590 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0137. Min Act: -0.0000

Data Index: 452132 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0131. Min Act: -0.0000

Data Index: 1939117 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0130. Min Act: -0.0000

Data Index: 1161851 (The Pile)

Max Activating Token Index: 464

Text #11

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0127. Min Act: -0.0000

Data Index: 218 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0118. Min Act: -0.0000

Data Index: 1169620 (The Pile)

Max Activating Token Index: 759

Text #13

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0120. Min Act: -0.0000

Data Index: 1350977 (The Pile)

Max Activating Token Index: 623

Text #14

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0123. Min Act: -0.0001

Data Index: 1921832 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0118. Min Act: -0.0000

Data Index: 242651 (The Pile)

Max Activating Token Index: 422

Text #16

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0127. Min Act: -0.0000

Data Index: 1034846 (The Pile)

Max Activating Token Index: 334

Text #17

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0124. Min Act: -0.0000

Data Index: 26723 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0121. Min Act: -0.0000

Data Index: 1288360 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0118. Min Act: -0.0000

Data Index: 215463 (The Pile)

Max Activating Token Index: 241