Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1572 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0273. Min Act: -0.0004

Data Index: 1598829 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0249. Min Act: -0.0004

Data Index: 1484021 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0201. Min Act: -0.0004

Data Index: 1474291 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0172. Min Act: -0.0004

Data Index: 1465764 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0175. Min Act: -0.0004

Data Index: 881533 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0175. Min Act: -0.0004

Data Index: 1530042 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0172. Min Act: -0.0004

Data Index: 1462675 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0175. Min Act: -0.0004

Data Index: 1627592 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0176. Min Act: -0.0004

Data Index: 236296 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0147. Min Act: -0.0004

Data Index: 1494871 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0143. Min Act: -0.0004

Data Index: 1652332 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0139. Min Act: -0.0004

Data Index: 3657 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0139. Min Act: -0.0004

Data Index: 1591785 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0148. Min Act: -0.0004

Data Index: 1104386 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0147. Min Act: -0.0004

Data Index: 1439608 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0139. Min Act: -0.0004

Data Index: 1417795 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0140. Min Act: -0.0004

Data Index: 1517239 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0141. Min Act: -0.0004

Data Index: 1492889 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0135. Min Act: -0.0004

Data Index: 1493216 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0132. Min Act: -0.0004

Data Index: 413442 (C4 (Web Text))

Max Activating Token Index: 140