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

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

Neuron 598 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: 1.3373. Min Range: -1.3373

Max Act: 1.3373. Min Act: -0.0000

Data Index: 435336 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 1.3373. Min Range: -1.3373

Max Act: 1.2217. Min Act: -0.0000

Data Index: 922268 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 1.3373. Min Range: -1.3373

Max Act: 1.1407. Min Act: -0.0000

Data Index: 164631 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 1.3373. Min Range: -1.3373

Max Act: 1.0426. Min Act: -0.0000

Data Index: 1179452 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 1.3373. Min Range: -1.3373

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1139070 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 1.3373. Min Range: -1.3373

Max Act: 1.0736. Min Act: -0.0000

Data Index: 20132 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 1.3373. Min Range: -1.3373

Max Act: 1.0337. Min Act: 0.0000

Data Index: 1277804 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 1.3373. Min Range: -1.3373

Max Act: 1.0628. Min Act: -0.0000

Data Index: 368712 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 1.3373. Min Range: -1.3373

Max Act: 1.0014. Min Act: -0.0000

Data Index: 648324 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.3373. Min Range: -1.3373

Max Act: 0.9733. Min Act: -0.0000

Data Index: 867677 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 1.3373. Min Range: -1.3373

Max Act: 0.9694. Min Act: -0.0000

Data Index: 501170 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.3373. Min Range: -1.3373

Max Act: 0.9406. Min Act: -0.0000

Data Index: 36852 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 1.3373. Min Range: -1.3373

Max Act: 0.9648. Min Act: -0.0000

Data Index: 123064 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 1.3373. Min Range: -1.3373

Max Act: 1.0822. Min Act: -0.0000

Data Index: 860752 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.3373. Min Range: -1.3373

Max Act: 0.9753. Min Act: -0.0000

Data Index: 83324 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.3373. Min Range: -1.3373

Max Act: 0.8679. Min Act: -0.0000

Data Index: 616568 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 1.3373. Min Range: -1.3373

Max Act: 1.0257. Min Act: -0.0000

Data Index: 544438 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.3373. Min Range: -1.3373

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1034172 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 1.3373. Min Range: -1.3373

Max Act: 0.9244. Min Act: -0.0000

Data Index: 281772 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 1.3373. Min Range: -1.3373

Max Act: 0.9405. Min Act: -0.0000

Data Index: 145856 (C4 (Web Text))

Max Activating Token Index: 867