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

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

Neuron 3492 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0316. Min Range: -1.0316

Max Act: 1.0124. Min Act: -0.0000

Data Index: 655248 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 1.0316. Min Range: -1.0316

Max Act: 1.0316. Min Act: -0.0000

Data Index: 72859 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.9086. Min Act: -0.0000

Data Index: 36493 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.9102. Min Act: -0.0001

Data Index: 1337060 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8923. Min Act: -0.0000

Data Index: 347967 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8552. Min Act: -0.0000

Data Index: 834722 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8579. Min Act: -0.0000

Data Index: 525387 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1187817 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.9008. Min Act: -0.0000

Data Index: 738713 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8462. Min Act: -0.0000

Data Index: 279768 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8685. Min Act: -0.0000

Data Index: 396628 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1219466 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.9192. Min Act: -0.0000

Data Index: 895928 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1100594 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.9169. Min Act: -0.0000

Data Index: 469364 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8492. Min Act: -0.0000

Data Index: 90338 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8557. Min Act: -0.0000

Data Index: 127053 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8442. Min Act: -0.0000

Data Index: 412138 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.7980. Min Act: -0.0000

Data Index: 857649 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8975. Min Act: -0.0000

Data Index: 719472 (C4 (Web Text))

Max Activating Token Index: 1000