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

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

Neuron 5833 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4444. Min Act: -0.0000

Data Index: 256647 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4392. Min Act: -0.0000

Data Index: 207241 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4442. Min Act: -0.0000

Data Index: 120085 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1055301 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3825. Min Act: -0.0000

Data Index: 396522 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3620. Min Act: -0.0000

Data Index: 438855 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1196953 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3551. Min Act: -0.0000

Data Index: 819500 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3649. Min Act: -0.0000

Data Index: 883265 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3626. Min Act: -0.0000

Data Index: 240420 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3553. Min Act: -0.0000

Data Index: 418767 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1325740 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1061673 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3236. Min Act: -0.0000

Data Index: 271236 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3539. Min Act: -0.0000

Data Index: 310009 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1314307 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3379. Min Act: -0.0000

Data Index: 656076 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1062288 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3454. Min Act: -0.0000

Data Index: 326922 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3209. Min Act: -0.0000

Data Index: 720451 (C4 (Web Text))

Max Activating Token Index: 157