Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2211 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.2160. Min Act: -0.0001

Data Index: 228402 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.2301. Min Act: -0.0001

Data Index: 885982 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.2305. Min Act: -0.0001

Data Index: 170862 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.2169. Min Act: -0.0001

Data Index: 908530 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.2130. Min Act: -0.0001

Data Index: 1169675 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1871. Min Act: -0.0001

Data Index: 1159880 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1822. Min Act: -0.0001

Data Index: 356557 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.2021. Min Act: -0.0001

Data Index: 774494 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1910. Min Act: -0.0001

Data Index: 1209286 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1307438 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1935. Min Act: -0.0001

Data Index: 1175580 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1857. Min Act: -0.0001

Data Index: 636804 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1845. Min Act: -0.0001

Data Index: 48929 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1806. Min Act: -0.0001

Data Index: 344949 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1771. Min Act: -0.0001

Data Index: 268955 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1730. Min Act: -0.0001

Data Index: 467092 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1554. Min Act: -0.0001

Data Index: 591766 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1665. Min Act: -0.0001

Data Index: 680225 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1795. Min Act: -0.0001

Data Index: 767106 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1692. Min Act: -0.0001

Data Index: 889746 (C4 (Web Text))

Max Activating Token Index: 148