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

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

Neuron 600 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: 0.0142. Min Range: -0.0142

Max Act: 0.0142. Min Act: -0.0006

Data Index: 965122 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0129. Min Act: -0.0006

Data Index: 88701 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1453344 (Python Code)

Max Activating Token Index: 499

Text #3

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0126. Min Act: -0.0006

Data Index: 861582 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0127. Min Act: -0.0006

Data Index: 831687 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0139. Min Act: -0.0006

Data Index: 531543 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0124. Min Act: -0.0006

Data Index: 650482 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1617189 (Python Code)

Max Activating Token Index: 335

Text #8

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1180984 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0113. Min Act: -0.0006

Data Index: 964061 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1096957 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1578417 (Python Code)

Max Activating Token Index: 415

Text #12

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0120. Min Act: -0.0006

Data Index: 927550 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0120. Min Act: -0.0006

Data Index: 849622 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0106. Min Act: -0.0006

Data Index: 489399 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0113. Min Act: -0.0006

Data Index: 591938 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0116. Min Act: -0.0006

Data Index: 545444 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0113. Min Act: -0.0006

Data Index: 27432 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0098. Min Act: -0.0006

Data Index: 121776 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1190023 (C4 (Web Text))

Max Activating Token Index: 407