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

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

Neuron 1261 in Layer 0

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: 0.3060. Min Range: -0.3060

Max Act: 0.3060. Min Act: -0.0001

Data Index: 82329 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2879. Min Act: -0.0001

Data Index: 301492 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2802. Min Act: -0.0001

Data Index: 484478 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2830. Min Act: -0.0001

Data Index: 439579 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2780. Min Act: -0.0001

Data Index: 699167 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2672. Min Act: -0.0001

Data Index: 825894 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2549. Min Act: -0.0002

Data Index: 469333 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2517. Min Act: -0.0001

Data Index: 1114995 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2525. Min Act: -0.0001

Data Index: 216844 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2483. Min Act: -0.0001

Data Index: 967740 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2385. Min Act: -0.0001

Data Index: 424929 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2368. Min Act: -0.0001

Data Index: 471218 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2407. Min Act: -0.0001

Data Index: 417872 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2355. Min Act: -0.0001

Data Index: 1243045 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2368. Min Act: -0.0001

Data Index: 106678 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2380. Min Act: -0.0001

Data Index: 522855 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2359. Min Act: -0.0001

Data Index: 923358 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2351. Min Act: -0.0001

Data Index: 490184 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2350. Min Act: -0.0001

Data Index: 725218 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2319. Min Act: -0.0001

Data Index: 650077 (C4 (Web Text))

Max Activating Token Index: 480