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

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

Neuron 4221 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1118043 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0353. Min Act: -0.0000

Data Index: 513866 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0338. Min Act: -0.0000

Data Index: 101647 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1404260 (Python Code)

Max Activating Token Index: 553

Text #4

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0333. Min Act: -0.0000

Data Index: 632761 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0315. Min Act: -0.0000

Data Index: 14651 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0348. Min Act: -0.0000

Data Index: 964091 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0313. Min Act: -0.0000

Data Index: 450609 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1186835 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1164561 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0300. Min Act: -0.0000

Data Index: 726651 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0294. Min Act: -0.0000

Data Index: 471870 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0301. Min Act: -0.0000

Data Index: 1201304 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0293. Min Act: -0.0000

Data Index: 1550652 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0293. Min Act: -0.0000

Data Index: 1489868 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0293. Min Act: -0.0000

Data Index: 1445401 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0289. Min Act: -0.0000

Data Index: 567879 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0284. Min Act: -0.0000

Data Index: 1025981 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0329. Min Act: -0.0000

Data Index: 844469 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.0582. Min Range: -0.0582

Max Act: 0.0239. Min Act: -0.0000

Data Index: 1135238 (C4 (Web Text))

Max Activating Token Index: 472