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

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

Neuron 480 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: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1525015 (Python Code)

Max Activating Token Index: 1008

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1552179 (Python Code)

Max Activating Token Index: 975

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1598508 (Python Code)

Max Activating Token Index: 1007

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1425299 (Python Code)

Max Activating Token Index: 907

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1484591 (Python Code)

Max Activating Token Index: 889

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1552817 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0410. Min Act: -0.0002

Data Index: 655750 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1453320 (Python Code)

Max Activating Token Index: 809

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1567460 (Python Code)

Max Activating Token Index: 180

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1512513 (Python Code)

Max Activating Token Index: 742

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0329. Min Act: -0.0002

Data Index: 77568 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1611075 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1597949 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1530621 (Python Code)

Max Activating Token Index: 952

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0297. Min Act: -0.0002

Data Index: 777213 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1484740 (Python Code)

Max Activating Token Index: 998

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0296. Min Act: -0.0002

Data Index: 63942 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1383941 (Python Code)

Max Activating Token Index: 1008

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1632086 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1508542 (Python Code)

Max Activating Token Index: 147