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

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

Neuron 2103 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: 0.2215. Min Range: -0.2215

Max Act: 0.2215. Min Act: -0.0002

Data Index: 919469 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2107. Min Act: -0.0002

Data Index: 594588 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2077. Min Act: -0.0002

Data Index: 469136 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2047. Min Act: -0.0003

Data Index: 80120 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2023. Min Act: -0.0002

Data Index: 571732 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2014. Min Act: -0.0002

Data Index: 542386 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1968. Min Act: -0.0002

Data Index: 1212135 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1966. Min Act: -0.0002

Data Index: 1083316 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1932. Min Act: -0.0003

Data Index: 735563 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1893. Min Act: -0.0003

Data Index: 515201 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1924. Min Act: -0.0002

Data Index: 271988 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1903. Min Act: -0.0003

Data Index: 586322 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1859. Min Act: -0.0002

Data Index: 258853 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1874. Min Act: -0.0003

Data Index: 790528 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1841. Min Act: -0.0003

Data Index: 744 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1855. Min Act: -0.0002

Data Index: 1304275 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1824. Min Act: -0.0002

Data Index: 318923 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1801. Min Act: -0.0003

Data Index: 657164 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1820. Min Act: -0.0002

Data Index: 903617 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1828. Min Act: -0.0002

Data Index: 878161 (C4 (Web Text))

Max Activating Token Index: 581