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

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

Neuron 3430 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2963. Min Act: -0.0000

Data Index: 808475 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2788. Min Act: -0.0000

Data Index: 680476 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2381. Min Act: -0.0000

Data Index: 844413 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1149299 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1963. Min Act: -0.0001

Data Index: 201208 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1014961 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2125. Min Act: -0.0001

Data Index: 151094 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2239. Min Act: -0.0001

Data Index: 139438 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2009. Min Act: -0.0000

Data Index: 151659 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2173. Min Act: -0.0001

Data Index: 869112 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1325901 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2206. Min Act: -0.0000

Data Index: 553287 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1899. Min Act: -0.0001

Data Index: 200213 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1716. Min Act: -0.0001

Data Index: 820248 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1949. Min Act: -0.0000

Data Index: 556905 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1343036 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1702. Min Act: -0.0001

Data Index: 349919 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2121. Min Act: -0.0000

Data Index: 655233 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1812. Min Act: -0.0001

Data Index: 739697 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1224177 (C4 (Web Text))

Max Activating Token Index: 76