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

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

Neuron 3410 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.6123. Min Act: -0.0000

Data Index: 258873 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.9836. Min Act: -0.0000

Data Index: 1642164 (Python Code)

Max Activating Token Index: 870

Text #2

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.5800. Min Act: 0.0000

Data Index: 259021 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.8468. Min Act: -0.0000

Data Index: 412736 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.9527. Min Act: 0.0000

Data Index: 532243 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.7582. Min Act: 0.0000

Data Index: 8202 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.5794. Min Act: 0.0001

Data Index: 671893 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.6536. Min Act: -0.0000

Data Index: 1391876 (Python Code)

Max Activating Token Index: 1011

Text #8

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.4973. Min Act: 0.0000

Data Index: 1123897 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.6252. Min Act: -0.0000

Data Index: 848941 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.4862. Min Act: -0.0000

Data Index: 1237223 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.6389. Min Act: 0.0000

Data Index: 454265 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.2157. Min Act: -0.0000

Data Index: 1655976 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.4399. Min Act: -0.0000

Data Index: 1274807 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.3427. Min Act: -0.0000

Data Index: 1430218 (Python Code)

Max Activating Token Index: 153

Text #15

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.4092. Min Act: -0.0000

Data Index: 1564021 (Python Code)

Max Activating Token Index: 268

Text #16

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.2889. Min Act: -0.0000

Data Index: 1141343 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.3962. Min Act: -0.0000

Data Index: 1599884 (Python Code)

Max Activating Token Index: 719

Text #18

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.4340. Min Act: -0.0000

Data Index: 1545830 (Python Code)

Max Activating Token Index: 511

Text #19

Max Range: 3.6123. Min Range: -3.6123

Max Act: 2.0654. Min Act: 0.0000

Data Index: 902923 (C4 (Web Text))

Max Activating Token Index: 652