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

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

Neuron 5356 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: 0.0590. Min Range: -0.0590

Max Act: 0.0590. Min Act: -0.0000

Data Index: 971944 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0524. Min Act: -0.0000

Data Index: 487726 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0547. Min Act: -0.0000

Data Index: 330069 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0493. Min Act: -0.0000

Data Index: 406952 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0475. Min Act: -0.0000

Data Index: 201362 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0466. Min Act: -0.0000

Data Index: 809280 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0467. Min Act: -0.0000

Data Index: 1183705 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0412. Min Act: -0.0000

Data Index: 1205537 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0437. Min Act: -0.0000

Data Index: 1000163 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0424. Min Act: -0.0000

Data Index: 590057 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0418. Min Act: -0.0000

Data Index: 853993 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0431. Min Act: -0.0000

Data Index: 989432 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0426. Min Act: -0.0000

Data Index: 300226 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0414. Min Act: -0.0000

Data Index: 779233 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0426. Min Act: -0.0000

Data Index: 1222372 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0404. Min Act: -0.0000

Data Index: 995425 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0398. Min Act: -0.0000

Data Index: 21339 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0408. Min Act: -0.0000

Data Index: 118101 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0420. Min Act: -0.0000

Data Index: 337847 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0390. Min Act: -0.0000

Data Index: 1228442 (C4 (Web Text))

Max Activating Token Index: 34