Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2602 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1564933 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5340. Min Act: -0.0000

Data Index: 915425 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5645. Min Act: -0.0000

Data Index: 988828 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5166. Min Act: -0.0000

Data Index: 237602 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5232. Min Act: -0.0000

Data Index: 127242 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5274. Min Act: -0.0000

Data Index: 787743 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4429. Min Act: -0.0000

Data Index: 787614 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4694. Min Act: -0.0000

Data Index: 86983 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4601. Min Act: -0.0000

Data Index: 763736 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4798. Min Act: -0.0000

Data Index: 397108 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4765. Min Act: -0.0000

Data Index: 70457 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4712. Min Act: -0.0000

Data Index: 119088 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4215. Min Act: -0.0000

Data Index: 122101 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4296. Min Act: -0.0000

Data Index: 897903 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4263. Min Act: -0.0000

Data Index: 878992 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1002687 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4133. Min Act: -0.0000

Data Index: 260699 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4409. Min Act: -0.0000

Data Index: 227911 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4020. Min Act: -0.0000

Data Index: 933748 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1181535 (C4 (Web Text))

Max Activating Token Index: 462