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

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

Neuron 1217 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5972. Min Act: -0.0001

Data Index: 854128 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5496. Min Act: -0.0001

Data Index: 574639 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4288. Min Act: -0.0001

Data Index: 146080 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3661. Min Act: -0.0001

Data Index: 82144 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3404. Min Act: -0.0001

Data Index: 604887 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3728. Min Act: -0.0001

Data Index: 1214223 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3609. Min Act: -0.0001

Data Index: 1139291 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3597. Min Act: -0.0001

Data Index: 1648713 (Python Code)

Max Activating Token Index: 840

Text #8

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3356. Min Act: -0.0001

Data Index: 876646 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3553. Min Act: -0.0001

Data Index: 599096 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3291. Min Act: -0.0001

Data Index: 715450 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3485. Min Act: -0.0001

Data Index: 151697 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3256. Min Act: -0.0001

Data Index: 607354 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3328. Min Act: -0.0001

Data Index: 74018 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3426. Min Act: -0.0001

Data Index: 1489902 (Python Code)

Max Activating Token Index: 216

Text #15

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3292. Min Act: -0.0001

Data Index: 443222 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3419. Min Act: -0.0001

Data Index: 195584 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3134. Min Act: -0.0001

Data Index: 576672 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1202541 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3188. Min Act: -0.0001

Data Index: 1169910 (C4 (Web Text))

Max Activating Token Index: 198