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

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

Neuron 4293 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1167974 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0599. Min Act: -0.0001

Data Index: 340674 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0001

Data Index: 257338 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1059061 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0473. Min Act: -0.0001

Data Index: 600357 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1055195 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0430. Min Act: -0.0001

Data Index: 112006 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0466. Min Act: -0.0001

Data Index: 829834 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0464. Min Act: -0.0002

Data Index: 846405 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0482. Min Act: -0.0001

Data Index: 582837 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0454. Min Act: -0.0001

Data Index: 73373 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1141469 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1283319 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0408. Min Act: -0.0001

Data Index: 1531648 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0461. Min Act: -0.0001

Data Index: 512155 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0365. Min Act: -0.0001

Data Index: 756314 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1460644 (Python Code)

Max Activating Token Index: 2

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1406624 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0389. Min Act: -0.0001

Data Index: 1359681 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0365. Min Act: -0.0001

Data Index: 784774 (C4 (Web Text))

Max Activating Token Index: 884