Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 861 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.7069. Min Act: -0.0000

Data Index: 966883 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.7034. Min Act: -0.0000

Data Index: 445825 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6817. Min Act: -0.0000

Data Index: 814708 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6801. Min Act: -0.0000

Data Index: 356393 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6512. Min Act: -0.0000

Data Index: 750173 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6463. Min Act: -0.0000

Data Index: 305055 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6410. Min Act: -0.0000

Data Index: 648351 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6424. Min Act: -0.0000

Data Index: 450274 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6606. Min Act: -0.0000

Data Index: 987964 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6402. Min Act: -0.0000

Data Index: 152765 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1009711 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6201. Min Act: -0.0000

Data Index: 802051 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1042351 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6029. Min Act: -0.0000

Data Index: 546552 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6275. Min Act: -0.0000

Data Index: 479216 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6235. Min Act: -0.0000

Data Index: 66290 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6227. Min Act: -0.0000

Data Index: 222384 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6233. Min Act: -0.0000

Data Index: 490200 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6230. Min Act: -0.0000

Data Index: 88205 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5957. Min Act: -0.0000

Data Index: 177634 (C4 (Web Text))

Max Activating Token Index: 158