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

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

Neuron 881 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2532. Min Act: -0.0001

Data Index: 1332810 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2470. Min Act: -0.0001

Data Index: 348648 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2432. Min Act: -0.0001

Data Index: 1338678 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2310. Min Act: -0.0001

Data Index: 385440 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2126. Min Act: -0.0001

Data Index: 48300 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2076. Min Act: -0.0001

Data Index: 1138467 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2116. Min Act: -0.0001

Data Index: 69187 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1868. Min Act: -0.0001

Data Index: 682312 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1741. Min Act: -0.0001

Data Index: 976028 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1869. Min Act: -0.0001

Data Index: 86171 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2031. Min Act: -0.0001

Data Index: 631240 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1980. Min Act: -0.0001

Data Index: 967272 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2203. Min Act: -0.0001

Data Index: 640463 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1905. Min Act: -0.0001

Data Index: 202753 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1166134 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1202955 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1878. Min Act: -0.0001

Data Index: 159817 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1862. Min Act: -0.0002

Data Index: 1279945 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1935. Min Act: -0.0001

Data Index: 1233526 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1939. Min Act: -0.0001

Data Index: 11858 (C4 (Web Text))

Max Activating Token Index: 858