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

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

Neuron 5069 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0001

Data Index: 1645810 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1571025 (Python Code)

Max Activating Token Index: 729

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1623940 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1486383 (Python Code)

Max Activating Token Index: 198

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1433029 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1419899 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1564939 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1581896 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1608444 (Python Code)

Max Activating Token Index: 118

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0140. Min Act: -0.0001

Data Index: 1552433 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1518486 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1563933 (Python Code)

Max Activating Token Index: 925

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1397943 (Python Code)

Max Activating Token Index: 568

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1391737 (Python Code)

Max Activating Token Index: 69

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1527698 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1471169 (Python Code)

Max Activating Token Index: 739

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0136. Min Act: -0.0001

Data Index: 1468186 (Python Code)

Max Activating Token Index: 486

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1390168 (Python Code)

Max Activating Token Index: 344

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1468113 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1508270 (Python Code)

Max Activating Token Index: 390