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

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

Neuron 1133 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1036216 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2464. Min Act: -0.0000

Data Index: 235613 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2263. Min Act: -0.0000

Data Index: 74637 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2245. Min Act: -0.0000

Data Index: 81404 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2166. Min Act: -0.0000

Data Index: 149509 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2137. Min Act: -0.0000

Data Index: 706770 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1101894 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1914. Min Act: -0.0001

Data Index: 1539496 (Python Code)

Max Activating Token Index: 728

Text #8

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2109. Min Act: -0.0000

Data Index: 184666 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2027. Min Act: -0.0001

Data Index: 1596464 (Python Code)

Max Activating Token Index: 884

Text #10

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2038. Min Act: -0.0001

Data Index: 1572670 (Python Code)

Max Activating Token Index: 751

Text #11

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1958. Min Act: -0.0000

Data Index: 702286 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1963. Min Act: -0.0000

Data Index: 1525119 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1558835 (Python Code)

Max Activating Token Index: 687

Text #14

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1627226 (Python Code)

Max Activating Token Index: 791

Text #15

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1566278 (Python Code)

Max Activating Token Index: 415

Text #16

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1899. Min Act: -0.0000

Data Index: 733048 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1854. Min Act: -0.0001

Data Index: 1521626 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1792. Min Act: -0.0000

Data Index: 998339 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1577831 (Python Code)

Max Activating Token Index: 911