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

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

Neuron 578 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.5108. Min Act: -0.0000

Data Index: 214947 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4549. Min Act: -0.0000

Data Index: 274043 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4570. Min Act: -0.0000

Data Index: 681967 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1486174 (Python Code)

Max Activating Token Index: 791

Text #4

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3971. Min Act: -0.0000

Data Index: 707971 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1103063 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1639897 (Python Code)

Max Activating Token Index: 418

Text #7

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3849. Min Act: -0.0001

Data Index: 1546976 (Python Code)

Max Activating Token Index: 986

Text #8

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3799. Min Act: -0.0000

Data Index: 685122 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3915. Min Act: -0.0000

Data Index: 785526 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1425759 (Python Code)

Max Activating Token Index: 655

Text #11

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1168788 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3693. Min Act: -0.0000

Data Index: 231054 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3597. Min Act: -0.0000

Data Index: 847975 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1268501 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3541. Min Act: -0.0000

Data Index: 17394 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1597554 (Python Code)

Max Activating Token Index: 451

Text #17

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1621515 (Python Code)

Max Activating Token Index: 256

Text #18

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1643416 (Python Code)

Max Activating Token Index: 837

Text #19

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3557. Min Act: -0.0000

Data Index: 491910 (C4 (Web Text))

Max Activating Token Index: 993