Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1434 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1467018 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1263269 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1494890 (Python Code)

Max Activating Token Index: 126

Text #3

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1202. Min Act: -0.0000

Data Index: 53563 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1075. Min Act: -0.0000

Data Index: 705233 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1617935 (Python Code)

Max Activating Token Index: 832

Text #6

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1061. Min Act: -0.0001

Data Index: 372315 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1319172 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1012712 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1097940 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1654592 (Python Code)

Max Activating Token Index: 197

Text #11

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0780. Min Act: -0.0000

Data Index: 35379 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1625976 (Python Code)

Max Activating Token Index: 486

Text #13

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0835. Min Act: -0.0001

Data Index: 1458814 (Python Code)

Max Activating Token Index: 694

Text #14

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1369407 (Python Code)

Max Activating Token Index: 1014

Text #15

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0816. Min Act: -0.0000

Data Index: 78579 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0857. Min Act: -0.0000

Data Index: 808282 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1408251 (Python Code)

Max Activating Token Index: 434

Text #18

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0851. Min Act: -0.0000

Data Index: 553335 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1414511 (Python Code)

Max Activating Token Index: 615