Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2500 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.3530. Min Act: -0.0000

Data Index: 345595 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.1506. Min Act: -0.0000

Data Index: 155241 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.1809. Min Act: -0.0000

Data Index: 789174 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.1335. Min Act: -0.0000

Data Index: 502823 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.1536. Min Act: -0.0000

Data Index: 252067 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.1417. Min Act: -0.0000

Data Index: 977576 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.1245. Min Act: -0.0000

Data Index: 651208 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.1117. Min Act: -0.0000

Data Index: 406019 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.1090. Min Act: -0.0000

Data Index: 287832 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1262114 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.0970. Min Act: -0.0000

Data Index: 362707 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1212813 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1191490 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1114306 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.0884. Min Act: -0.0000

Data Index: 969552 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.0769. Min Act: -0.0000

Data Index: 421217 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.0820. Min Act: -0.0000

Data Index: 266109 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.0819. Min Act: -0.0000

Data Index: 264322 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.0835. Min Act: -0.0000

Data Index: 1319888 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.0682. Min Act: -0.0000

Data Index: 401737 (C4 (Web Text))

Max Activating Token Index: 26