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

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

Neuron 5339 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2352. Min Act: -0.0002

Data Index: 658579 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2205. Min Act: -0.0002

Data Index: 1078649 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2152. Min Act: -0.0002

Data Index: 8492 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2066. Min Act: -0.0002

Data Index: 929176 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2072. Min Act: -0.0002

Data Index: 830467 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1989. Min Act: -0.0002

Data Index: 637124 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1957. Min Act: -0.0002

Data Index: 1353352 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1910. Min Act: -0.0002

Data Index: 88275 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1933. Min Act: -0.0002

Data Index: 760805 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1930. Min Act: -0.0002

Data Index: 175303 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1911. Min Act: -0.0002

Data Index: 786818 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1899. Min Act: -0.0002

Data Index: 503342 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1871. Min Act: -0.0002

Data Index: 200045 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1857. Min Act: -0.0003

Data Index: 665945 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1859. Min Act: -0.0003

Data Index: 258609 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1821. Min Act: -0.0002

Data Index: 919802 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1846. Min Act: -0.0002

Data Index: 213171 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1827. Min Act: -0.0002

Data Index: 411444 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1869. Min Act: -0.0002

Data Index: 645845 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1813. Min Act: -0.0002

Data Index: 47796 (C4 (Web Text))

Max Activating Token Index: 885