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

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

Neuron 3969 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.2653. Min Act: -0.0001

Data Index: 404779 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.2266. Min Act: -0.0001

Data Index: 1249515 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.2233. Min Act: -0.0001

Data Index: 1063218 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.2131. Min Act: -0.0001

Data Index: 1183481 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.2118. Min Act: -0.0001

Data Index: 824390 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1982. Min Act: -0.0001

Data Index: 123584 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1931. Min Act: -0.0001

Data Index: 221073 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1904. Min Act: -0.0001

Data Index: 1089147 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1910. Min Act: -0.0001

Data Index: 68192 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1906. Min Act: -0.0001

Data Index: 385164 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1927. Min Act: -0.0001

Data Index: 909304 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1773. Min Act: -0.0001

Data Index: 833811 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1145208 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1810. Min Act: -0.0001

Data Index: 250729 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1318279 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1081892 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1725. Min Act: -0.0001

Data Index: 959665 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1757. Min Act: -0.0001

Data Index: 1317543 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1888. Min Act: -0.0001

Data Index: 1624539 (Python Code)

Max Activating Token Index: 760

Text #19

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1798. Min Act: -0.0001

Data Index: 1187229 (C4 (Web Text))

Max Activating Token Index: 872