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

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

Neuron 1890 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0261. Min Act: -0.0001

Data Index: 1561037 (Python Code)

Max Activating Token Index: 870

Text #1

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1539317 (Python Code)

Max Activating Token Index: 945

Text #2

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1604190 (Python Code)

Max Activating Token Index: 790

Text #3

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1557366 (Python Code)

Max Activating Token Index: 391

Text #4

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1518244 (Python Code)

Max Activating Token Index: 1005

Text #5

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1581713 (Python Code)

Max Activating Token Index: 724

Text #6

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1449394 (Python Code)

Max Activating Token Index: 910

Text #7

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1443185 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1446026 (Python Code)

Max Activating Token Index: 945

Text #9

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1367254 (Python Code)

Max Activating Token Index: 917

Text #10

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1647386 (Python Code)

Max Activating Token Index: 647

Text #11

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1480870 (Python Code)

Max Activating Token Index: 544

Text #12

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0186. Min Act: -0.0001

Data Index: 577631 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1582268 (Python Code)

Max Activating Token Index: 928

Text #14

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1545607 (Python Code)

Max Activating Token Index: 321

Text #15

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0175. Min Act: -0.0001

Data Index: 1066199 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1379731 (Python Code)

Max Activating Token Index: 974

Text #17

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1215145 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1481637 (Python Code)

Max Activating Token Index: 499

Text #19

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0169. Min Act: -0.0002

Data Index: 795502 (C4 (Web Text))

Max Activating Token Index: 779