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

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

Neuron 1224 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: 1.8234. Min Range: -1.8234

Max Act: 1.8234. Min Act: -0.0002

Data Index: 1276461 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.7932. Min Act: -0.0002

Data Index: 226754 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.7677. Min Act: -0.0002

Data Index: 496955 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.7748. Min Act: -0.0002

Data Index: 237761 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.7259. Min Act: -0.0002

Data Index: 367816 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.7153. Min Act: -0.0002

Data Index: 817864 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.6320. Min Act: -0.0002

Data Index: 442755 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.6202. Min Act: -0.0002

Data Index: 638401 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.6408. Min Act: -0.0002

Data Index: 387374 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.6219. Min Act: -0.0002

Data Index: 1072670 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.6858. Min Act: -0.0002

Data Index: 814214 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.6260. Min Act: -0.0002

Data Index: 1057815 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.5924. Min Act: -0.0002

Data Index: 216459 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.5717. Min Act: -0.0002

Data Index: 259947 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.5626. Min Act: -0.0002

Data Index: 972723 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.5509. Min Act: -0.0003

Data Index: 517581 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.5833. Min Act: -0.0002

Data Index: 561674 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.5510. Min Act: -0.0002

Data Index: 849806 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.5157. Min Act: -0.0002

Data Index: 913240 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 1.8234. Min Range: -1.8234

Max Act: 1.5334. Min Act: -0.0002

Data Index: 681620 (C4 (Web Text))

Max Activating Token Index: 840