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

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

Neuron 4911 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1417475 (Python Code)

Max Activating Token Index: 394

Text #1

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2602. Min Act: -0.0000

Data Index: 798959 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1263868 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2295. Min Act: -0.0000

Data Index: 206503 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1400057 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2219. Min Act: -0.0000

Data Index: 99977 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2297. Min Act: -0.0000

Data Index: 623777 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1138852 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2193. Min Act: -0.0000

Data Index: 698673 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2156. Min Act: -0.0000

Data Index: 510567 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1405259 (Python Code)

Max Activating Token Index: 114

Text #11

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2026. Min Act: -0.0000

Data Index: 162773 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2108. Min Act: -0.0000

Data Index: 593261 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2033. Min Act: -0.0000

Data Index: 174501 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2078. Min Act: -0.0000

Data Index: 451109 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2044. Min Act: -0.0000

Data Index: 666815 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1946. Min Act: -0.0000

Data Index: 966245 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1327726 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2007. Min Act: -0.0000

Data Index: 580525 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1543181 (Python Code)

Max Activating Token Index: 809