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

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

Neuron 4336 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1481004 (Python Code)

Max Activating Token Index: 961

Text #1

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1382960 (Python Code)

Max Activating Token Index: 594

Text #2

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2298. Min Act: -0.0000

Data Index: 250270 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2291. Min Act: -0.0000

Data Index: 845037 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2228. Min Act: -0.0000

Data Index: 309094 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1585336 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2214. Min Act: -0.0000

Data Index: 607200 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2134. Min Act: -0.0000

Data Index: 1611715 (Python Code)

Max Activating Token Index: 999

Text #8

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2077. Min Act: -0.0000

Data Index: 85578 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1656666 (Python Code)

Max Activating Token Index: 542

Text #10

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1402874 (Python Code)

Max Activating Token Index: 508

Text #11

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1189460 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1560942 (Python Code)

Max Activating Token Index: 739

Text #13

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.1847. Min Act: -0.0000

Data Index: 262926 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.1964. Min Act: -0.0000

Data Index: 326161 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1551154 (Python Code)

Max Activating Token Index: 941

Text #16

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1416266 (Python Code)

Max Activating Token Index: 360

Text #17

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1573518 (Python Code)

Max Activating Token Index: 701

Text #18

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1003824 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.1949. Min Act: -0.0000

Data Index: 845321 (C4 (Web Text))

Max Activating Token Index: 422