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

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

Neuron 1726 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.9421. Min Act: -0.0001

Data Index: 228745 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.9359. Min Act: -0.0001

Data Index: 1224987 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.9170. Min Act: -0.0001

Data Index: 275380 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8899. Min Act: -0.0001

Data Index: 864570 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8968. Min Act: -0.0001

Data Index: 537689 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.9138. Min Act: -0.0001

Data Index: 293531 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.9054. Min Act: -0.0001

Data Index: 1285866 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.9007. Min Act: -0.0001

Data Index: 897699 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8980. Min Act: -0.0001

Data Index: 52783 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8847. Min Act: -0.0001

Data Index: 754338 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8693. Min Act: -0.0001

Data Index: 985286 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8273. Min Act: -0.0001

Data Index: 897163 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8255. Min Act: -0.0001

Data Index: 746226 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8152. Min Act: -0.0001

Data Index: 696336 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8150. Min Act: -0.0001

Data Index: 1095845 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.7858. Min Act: -0.0001

Data Index: 1077187 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8059. Min Act: -0.0001

Data Index: 510883 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8121. Min Act: -0.0001

Data Index: 1015711 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.7675. Min Act: -0.0001

Data Index: 1248737 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.8307. Min Act: -0.0001

Data Index: 767748 (C4 (Web Text))

Max Activating Token Index: 785