Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1633 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1386992 (Python Code)

Max Activating Token Index: 340

Text #1

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1504412 (Python Code)

Max Activating Token Index: 754

Text #2

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0185. Min Act: -0.0006

Data Index: 1474007 (Python Code)

Max Activating Token Index: 892

Text #3

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1539544 (Python Code)

Max Activating Token Index: 620

Text #4

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1463662 (Python Code)

Max Activating Token Index: 93

Text #5

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1390083 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1559475 (Python Code)

Max Activating Token Index: 809

Text #7

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1576534 (Python Code)

Max Activating Token Index: 281

Text #8

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1553806 (Python Code)

Max Activating Token Index: 638

Text #9

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1376930 (Python Code)

Max Activating Token Index: 295

Text #10

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1528486 (Python Code)

Max Activating Token Index: 541

Text #11

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1479038 (Python Code)

Max Activating Token Index: 390

Text #12

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1400746 (Python Code)

Max Activating Token Index: 613

Text #13

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1593437 (Python Code)

Max Activating Token Index: 605

Text #14

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1525067 (Python Code)

Max Activating Token Index: 747

Text #15

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1598044 (Python Code)

Max Activating Token Index: 766

Text #16

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1488770 (Python Code)

Max Activating Token Index: 898

Text #17

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0173. Min Act: -0.0006

Data Index: 1436344 (Python Code)

Max Activating Token Index: 153

Text #18

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1401653 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1385956 (Python Code)

Max Activating Token Index: 751