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

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

Neuron 1806 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.5076. Min Act: -0.0001

Data Index: 56092 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.3245. Min Act: -0.0001

Data Index: 930642 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.3146. Min Act: -0.0001

Data Index: 1029157 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.4307. Min Act: -0.0001

Data Index: 719217 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.4409. Min Act: -0.0001

Data Index: 800736 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.3024. Min Act: -0.0001

Data Index: 957722 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.2494. Min Act: -0.0001

Data Index: 260983 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.2767. Min Act: -0.0001

Data Index: 913698 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.2999. Min Act: -0.0001

Data Index: 313920 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.2158. Min Act: -0.0001

Data Index: 1084672 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.2439. Min Act: -0.0001

Data Index: 1295105 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.2388. Min Act: -0.0001

Data Index: 844029 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.1691. Min Act: -0.0001

Data Index: 1115784 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.2457. Min Act: -0.0001

Data Index: 1158545 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.1857. Min Act: -0.0001

Data Index: 379864 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.1765. Min Act: -0.0001

Data Index: 1059699 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.0726. Min Act: -0.0001

Data Index: 59746 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.1320. Min Act: -0.0001

Data Index: 445201 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.1633. Min Act: -0.0001

Data Index: 644955 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 1.5076. Min Range: -1.5076

Max Act: 1.1953. Min Act: -0.0001

Data Index: 451710 (C4 (Web Text))

Max Activating Token Index: 65