Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3731 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1006849 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4091. Min Act: -0.0001

Data Index: 176364 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4157. Min Act: -0.0000

Data Index: 883794 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1351621 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1087509 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1187338 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1562370 (Python Code)

Max Activating Token Index: 388

Text #7

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3358. Min Act: -0.0001

Data Index: 1406721 (Python Code)

Max Activating Token Index: 650

Text #8

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1516197 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1285785 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3556. Min Act: -0.0001

Data Index: 1549005 (Python Code)

Max Activating Token Index: 1010

Text #11

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3543. Min Act: -0.0001

Data Index: 801545 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3408. Min Act: -0.0000

Data Index: 780745 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3394. Min Act: -0.0001

Data Index: 18385 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3514. Min Act: -0.0000

Data Index: 511080 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3570. Min Act: -0.0001

Data Index: 69631 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3536. Min Act: -0.0000

Data Index: 151353 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3283. Min Act: -0.0000

Data Index: 224335 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3372. Min Act: -0.0001

Data Index: 1589837 (Python Code)

Max Activating Token Index: 297

Text #19

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3398. Min Act: -0.0000

Data Index: 944420 (C4 (Web Text))

Max Activating Token Index: 299