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

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

Neuron 2997 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1338943 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.5771. Min Act: -0.0000

Data Index: 806407 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4738. Min Act: -0.0000

Data Index: 129040 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4344. Min Act: -0.0000

Data Index: 839455 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.5016. Min Act: -0.0000

Data Index: 951539 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.5422. Min Act: -0.0000

Data Index: 425498 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4571. Min Act: -0.0000

Data Index: 841016 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1368626 (Python Code)

Max Activating Token Index: 760

Text #8

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4918. Min Act: -0.0000

Data Index: 492038 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4575. Min Act: -0.0000

Data Index: 629453 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4563. Min Act: -0.0000

Data Index: 523059 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4532. Min Act: -0.0000

Data Index: 450653 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1205300 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4455. Min Act: -0.0000

Data Index: 180891 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1331087 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4240. Min Act: -0.0000

Data Index: 243271 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1287813 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.3521. Min Act: -0.0000

Data Index: 1085397 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.3411. Min Act: -0.0000

Data Index: 162411 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.3353. Min Act: -0.0000

Data Index: 244771 (C4 (Web Text))

Max Activating Token Index: 387