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

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

Neuron 1044 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: 0.5551. Min Range: -0.5551

Max Act: 0.5472. Min Act: -0.0002

Data Index: 1175669 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5437. Min Act: -0.0003

Data Index: 224767 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5551. Min Act: -0.0002

Data Index: 38586 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5419. Min Act: -0.0002

Data Index: 1257415 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5400. Min Act: -0.0002

Data Index: 946309 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5508. Min Act: -0.0002

Data Index: 953868 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5366. Min Act: -0.0002

Data Index: 178817 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5334. Min Act: -0.0003

Data Index: 491620 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5291. Min Act: -0.0002

Data Index: 1076804 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5302. Min Act: -0.0002

Data Index: 622299 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5269. Min Act: -0.0002

Data Index: 571373 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5360. Min Act: -0.0002

Data Index: 383486 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5289. Min Act: -0.0002

Data Index: 549172 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5217. Min Act: -0.0002

Data Index: 1024046 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5255. Min Act: -0.0002

Data Index: 1265675 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5157. Min Act: -0.0003

Data Index: 680592 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5199. Min Act: -0.0002

Data Index: 159272 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5283. Min Act: -0.0003

Data Index: 1304889 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5157. Min Act: -0.0002

Data Index: 1293351 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.5551. Min Range: -0.5551

Max Act: 0.5248. Min Act: -0.0003

Data Index: 222847 (C4 (Web Text))

Max Activating Token Index: 14