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

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

Neuron 1995 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1561638 (Python Code)

Max Activating Token Index: 859

Text #1

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0249. Min Act: -0.0003

Data Index: 727097 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1392765 (Python Code)

Max Activating Token Index: 920

Text #3

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1558400 (Python Code)

Max Activating Token Index: 893

Text #4

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1056180 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0216. Min Act: -0.0003

Data Index: 834526 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0227. Min Act: -0.0003

Data Index: 434774 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0181. Min Act: -0.0003

Data Index: 337023 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1415070 (Python Code)

Max Activating Token Index: 951

Text #9

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1433805 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1542977 (Python Code)

Max Activating Token Index: 864

Text #11

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1110974 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0171. Min Act: -0.0003

Data Index: 1386990 (Python Code)

Max Activating Token Index: 884

Text #13

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0179. Min Act: -0.0003

Data Index: 841318 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1514963 (Python Code)

Max Activating Token Index: 870

Text #15

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1503167 (Python Code)

Max Activating Token Index: 973

Text #16

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0179. Min Act: -0.0003

Data Index: 19732 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0198. Min Act: -0.0003

Data Index: 292396 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1354685 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1367692 (Python Code)

Max Activating Token Index: 857