Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 573 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0976. Min Range: -2.0976

Max Act: 2.0757. Min Act: -0.0000

Data Index: 740950 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 2.0976. Min Range: -2.0976

Max Act: 2.0717. Min Act: -0.0000

Data Index: 1224151 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.9040. Min Act: -0.0000

Data Index: 934623 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 2.0976. Min Range: -2.0976

Max Act: 2.0976. Min Act: -0.0000

Data Index: 934870 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.9592. Min Act: -0.0000

Data Index: 467193 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.9528. Min Act: -0.0000

Data Index: 1047738 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 2.0976. Min Range: -2.0976

Max Act: 2.0458. Min Act: -0.0000

Data Index: 217025 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.8318. Min Act: -0.0000

Data Index: 1159057 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.8279. Min Act: -0.0000

Data Index: 1030757 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.9355. Min Act: -0.0000

Data Index: 1236541 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.8075. Min Act: -0.0000

Data Index: 716681 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.9117. Min Act: -0.0000

Data Index: 776700 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.7937. Min Act: -0.0000

Data Index: 372514 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.8719. Min Act: -0.0000

Data Index: 959876 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.6330. Min Act: -0.0000

Data Index: 413977 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.9259. Min Act: -0.0000

Data Index: 400299 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.7272. Min Act: -0.0000

Data Index: 465073 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.5322. Min Act: -0.0000

Data Index: 274013 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.9019. Min Act: -0.0000

Data Index: 699398 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 2.0976. Min Range: -2.0976

Max Act: 1.7696. Min Act: -0.0000

Data Index: 571199 (C4 (Web Text))

Max Activating Token Index: 630