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

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

Neuron 2023 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0154. Min Act: -0.0002

Data Index: 979078 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0143. Min Act: -0.0002

Data Index: 148831 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0141. Min Act: -0.0002

Data Index: 409597 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1060045 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0141. Min Act: -0.0002

Data Index: 439002 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0132. Min Act: -0.0003

Data Index: 649913 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1247337 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1657 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0132. Min Act: -0.0003

Data Index: 504343 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0133. Min Act: -0.0002

Data Index: 337785 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0126. Min Act: -0.0002

Data Index: 651529 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0127. Min Act: -0.0002

Data Index: 976919 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1182020 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0122. Min Act: -0.0002

Data Index: 428662 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0125. Min Act: -0.0002

Data Index: 86243 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0121. Min Act: -0.0002

Data Index: 794888 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0120. Min Act: -0.0002

Data Index: 131837 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1207972 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1328622 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0120. Min Act: -0.0003

Data Index: 92332 (C4 (Web Text))

Max Activating Token Index: 519