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

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

Neuron 3679 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: 0.2191. Min Range: -0.2191

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1070372 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.2110. Min Act: -0.0001

Data Index: 72331 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1090200 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1295976 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1865. Min Act: -0.0001

Data Index: 253434 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1822. Min Act: -0.0001

Data Index: 240373 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1761. Min Act: -0.0001

Data Index: 41696 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1749. Min Act: -0.0001

Data Index: 1045962 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1684. Min Act: -0.0001

Data Index: 165694 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1676. Min Act: -0.0001

Data Index: 625549 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1715. Min Act: -0.0001

Data Index: 446149 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1211518 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1756. Min Act: -0.0001

Data Index: 1148067 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1783. Min Act: -0.0001

Data Index: 1057900 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1650. Min Act: -0.0001

Data Index: 417310 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1642. Min Act: -0.0001

Data Index: 497974 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1634. Min Act: -0.0001

Data Index: 104329 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1033895 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1597. Min Act: -0.0001

Data Index: 973545 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1592. Min Act: -0.0001

Data Index: 254947 (C4 (Web Text))

Max Activating Token Index: 872