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

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

Neuron 4311 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1394412 (Python Code)

Max Activating Token Index: 1010

Text #1

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0160. Min Act: -0.0002

Data Index: 1622423 (Python Code)

Max Activating Token Index: 971

Text #2

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1388063 (Python Code)

Max Activating Token Index: 893

Text #3

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1117290 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0131. Min Act: -0.0002

Data Index: 744563 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1570421 (Python Code)

Max Activating Token Index: 255

Text #6

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1363927 (Python Code)

Max Activating Token Index: 909

Text #7

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1608339 (Python Code)

Max Activating Token Index: 363

Text #8

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0143. Min Act: -0.0002

Data Index: 782199 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1612530 (Python Code)

Max Activating Token Index: 989

Text #10

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1622591 (Python Code)

Max Activating Token Index: 967

Text #11

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0140. Min Act: -0.0002

Data Index: 979723 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1595615 (Python Code)

Max Activating Token Index: 428

Text #13

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1528874 (Python Code)

Max Activating Token Index: 249

Text #14

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1396683 (Python Code)

Max Activating Token Index: 874

Text #15

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1347523 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1494697 (Python Code)

Max Activating Token Index: 345

Text #17

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0128. Min Act: -0.0002

Data Index: 885453 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0133. Min Act: -0.0002

Data Index: 64557 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1641133 (Python Code)

Max Activating Token Index: 980