Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1895 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2462. Min Act: -0.0001

Data Index: 502646 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2133. Min Act: -0.0001

Data Index: 1227556 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2033. Min Act: -0.0001

Data Index: 830373 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1948. Min Act: -0.0001

Data Index: 917619 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2090. Min Act: -0.0001

Data Index: 34477 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2162. Min Act: -0.0001

Data Index: 1243575 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1816. Min Act: -0.0001

Data Index: 1279501 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1943. Min Act: -0.0001

Data Index: 880537 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1715. Min Act: -0.0001

Data Index: 406984 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2144. Min Act: -0.0001

Data Index: 120657 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2118. Min Act: -0.0001

Data Index: 363895 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1944. Min Act: -0.0001

Data Index: 352156 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1221807 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1832. Min Act: -0.0001

Data Index: 623701 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1865. Min Act: -0.0001

Data Index: 139087 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1883. Min Act: -0.0001

Data Index: 68625 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1803. Min Act: -0.0001

Data Index: 292167 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1854. Min Act: -0.0001

Data Index: 82912 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1844. Min Act: -0.0001

Data Index: 862814 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1782. Min Act: -0.0001

Data Index: 98378 (C4 (Web Text))

Max Activating Token Index: 603