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

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

Neuron 4640 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.5860. Min Act: -0.0000

Data Index: 964489 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.5033. Min Act: 0.0000

Data Index: 70506 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.1463. Min Act: 0.0001

Data Index: 419264 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.2446. Min Act: -0.0000

Data Index: 1046046 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.9094. Min Act: -0.0000

Data Index: 350645 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.0100. Min Act: -0.0000

Data Index: 840168 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.9507. Min Act: -0.0000

Data Index: 1327007 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.8373. Min Act: 0.0000

Data Index: 1021366 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.1180. Min Act: -0.0000

Data Index: 777634 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.7574. Min Act: -0.0000

Data Index: 88804 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.7389. Min Act: -0.0000

Data Index: 472439 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.8128. Min Act: 0.0000

Data Index: 1256805 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.7130. Min Act: -0.0000

Data Index: 1216660 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.8273. Min Act: -0.0000

Data Index: 765151 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.8042. Min Act: -0.0000

Data Index: 1208595 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.7024. Min Act: -0.0000

Data Index: 13853 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.7067. Min Act: -0.0000

Data Index: 546452 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.7181. Min Act: -0.0000

Data Index: 980293 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.6863. Min Act: -0.0000

Data Index: 287952 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.7226. Min Act: -0.0000

Data Index: 559595 (C4 (Web Text))

Max Activating Token Index: 263