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

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

Neuron 3839 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2751. Min Act: -0.0000

Data Index: 755763 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2257. Min Act: -0.0000

Data Index: 253981 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2287. Min Act: -0.0000

Data Index: 413269 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2258. Min Act: -0.0000

Data Index: 136156 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1437643 (Python Code)

Max Activating Token Index: 189

Text #5

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2070. Min Act: -0.0000

Data Index: 443044 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1438575 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1612818 (Python Code)

Max Activating Token Index: 931

Text #8

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1859. Min Act: -0.0000

Data Index: 902934 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1126982 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1487280 (Python Code)

Max Activating Token Index: 301

Text #11

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1605. Min Act: -0.0000

Data Index: 741469 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1378886 (Python Code)

Max Activating Token Index: 180

Text #13

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1502796 (Python Code)

Max Activating Token Index: 189

Text #14

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1400. Min Act: -0.0000

Data Index: 605362 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1553300 (Python Code)

Max Activating Token Index: 458

Text #16

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1551. Min Act: -0.0000

Data Index: 584142 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1488. Min Act: -0.0000

Data Index: 170817 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1430. Min Act: -0.0000

Data Index: 612236 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1358061 (C4 (Web Text))

Max Activating Token Index: 968