Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4818 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1297596 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0163. Min Act: -0.0002

Data Index: 193460 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0144. Min Act: -0.0002

Data Index: 320961 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1491048 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1593511 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0136. Min Act: -0.0002

Data Index: 3079 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1457639 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0133. Min Act: -0.0002

Data Index: 255364 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1326265 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0141. Min Act: -0.0002

Data Index: 608495 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1516714 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1480207 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1314819 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0132. Min Act: -0.0002

Data Index: 847448 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1335755 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1204747 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1464569 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0115. Min Act: -0.0002

Data Index: 403427 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0136. Min Act: -0.0002

Data Index: 449209 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0123. Min Act: -0.0002

Data Index: 360208 (C4 (Web Text))

Max Activating Token Index: 3