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

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

Neuron 429 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0144. Min Act: -0.0006

Data Index: 910989 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0140. Min Act: -0.0006

Data Index: 559381 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0138. Min Act: -0.0006

Data Index: 609827 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1090392 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0132. Min Act: -0.0006

Data Index: 729248 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0132. Min Act: -0.0006

Data Index: 395260 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0125. Min Act: -0.0006

Data Index: 876281 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0127. Min Act: -0.0006

Data Index: 855756 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0121. Min Act: -0.0006

Data Index: 772703 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1077479 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0125. Min Act: -0.0006

Data Index: 16431 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0127. Min Act: -0.0006

Data Index: 118145 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0123. Min Act: -0.0006

Data Index: 702612 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1091200 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1318506 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0122. Min Act: -0.0006

Data Index: 807211 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0125. Min Act: -0.0006

Data Index: 727437 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0120. Min Act: -0.0006

Data Index: 179534 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0119. Min Act: -0.0006

Data Index: 208604 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0118. Min Act: -0.0006

Data Index: 172768 (C4 (Web Text))

Max Activating Token Index: 671