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

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

Neuron 2055 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: 0.1763. Min Range: -0.1763

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1607827 (Python Code)

Max Activating Token Index: 955

Text #1

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1505. Min Act: -0.0000

Data Index: 972012 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1380. Min Act: -0.0000

Data Index: 949378 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1365. Min Act: -0.0000

Data Index: 95196 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1486. Min Act: -0.0000

Data Index: 269712 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1595733 (Python Code)

Max Activating Token Index: 155

Text #6

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1255. Min Act: -0.0000

Data Index: 644615 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1166189 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1134. Min Act: -0.0000

Data Index: 175076 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1576969 (Python Code)

Max Activating Token Index: 673

Text #10

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1128. Min Act: -0.0000

Data Index: 29978 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1425558 (Python Code)

Max Activating Token Index: 288

Text #12

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1500784 (Python Code)

Max Activating Token Index: 657

Text #13

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1033. Min Act: -0.0000

Data Index: 42242 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1095. Min Act: -0.0000

Data Index: 821653 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1619940 (Python Code)

Max Activating Token Index: 932

Text #16

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.0983. Min Act: -0.0000

Data Index: 507965 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1376880 (Python Code)

Max Activating Token Index: 899

Text #18

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.0995. Min Act: -0.0000

Data Index: 654225 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1292596 (C4 (Web Text))

Max Activating Token Index: 759