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

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

Neuron 3534 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.7123. Min Act: -0.0002

Data Index: 973076 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.6093. Min Act: -0.0001

Data Index: 714520 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.5706. Min Act: -0.0001

Data Index: 842998 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.5795. Min Act: -0.0002

Data Index: 1028837 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3785. Min Act: -0.0002

Data Index: 340005 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.4132. Min Act: -0.0001

Data Index: 876637 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.2944. Min Act: -0.0002

Data Index: 641650 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.2876. Min Act: -0.0001

Data Index: 1113139 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.2999. Min Act: -0.0002

Data Index: 1207486 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.2834. Min Act: -0.0002

Data Index: 1313175 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.1828. Min Act: -0.0001

Data Index: 315904 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.2351. Min Act: -0.0002

Data Index: 1325567 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.1807. Min Act: -0.0002

Data Index: 843314 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.2049. Min Act: -0.0001

Data Index: 824985 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.2056. Min Act: -0.0002

Data Index: 682005 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.1660. Min Act: -0.0002

Data Index: 529823 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.1374. Min Act: -0.0001

Data Index: 998036 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.1631. Min Act: -0.0002

Data Index: 34399 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.2275. Min Act: -0.0002

Data Index: 833835 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.1167. Min Act: -0.0002

Data Index: 205111 (C4 (Web Text))

Max Activating Token Index: 786