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

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

Neuron 2036 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.3675. Min Act: -0.0000

Data Index: 573199 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2307. Min Act: -0.0001

Data Index: 266021 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2303. Min Act: -0.0000

Data Index: 121657 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2202. Min Act: -0.0001

Data Index: 815909 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2183. Min Act: -0.0000

Data Index: 698025 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2179. Min Act: -0.0000

Data Index: 748062 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1260558 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2092. Min Act: -0.0000

Data Index: 423912 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2134. Min Act: -0.0000

Data Index: 688196 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.1911. Min Act: -0.0000

Data Index: 491035 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.2035. Min Act: -0.0001

Data Index: 1124380 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.1895. Min Act: -0.0000

Data Index: 938614 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.1939. Min Act: -0.0001

Data Index: 733373 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.1861. Min Act: -0.0000

Data Index: 896512 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.1871. Min Act: -0.0000

Data Index: 277796 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.1860. Min Act: -0.0001

Data Index: 1312232 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.1888. Min Act: -0.0000

Data Index: 874961 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1051688 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.1730. Min Act: -0.0000

Data Index: 142990 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.3675. Min Range: -0.3675

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1000494 (C4 (Web Text))

Max Activating Token Index: 305