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

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

Neuron 482 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.0413. Min Range: -9.0413

Max Act: 9.0413. Min Act: -0.0000

Data Index: 50592 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 9.0413. Min Range: -9.0413

Max Act: 8.3405. Min Act: -0.0000

Data Index: 286286 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 9.0413. Min Range: -9.0413

Max Act: 8.3871. Min Act: -0.0000

Data Index: 434669 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 9.0413. Min Range: -9.0413

Max Act: 8.3547. Min Act: -0.0000

Data Index: 1215921 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 9.0413. Min Range: -9.0413

Max Act: 7.8529. Min Act: -0.0000

Data Index: 457937 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 9.0413. Min Range: -9.0413

Max Act: 7.8358. Min Act: -0.0000

Data Index: 577511 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 9.0413. Min Range: -9.0413

Max Act: 7.9971. Min Act: -0.0000

Data Index: 825618 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 9.0413. Min Range: -9.0413

Max Act: 7.4653. Min Act: -0.0000

Data Index: 498903 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 9.0413. Min Range: -9.0413

Max Act: 7.4258. Min Act: -0.0000

Data Index: 379941 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 9.0413. Min Range: -9.0413

Max Act: 7.3892. Min Act: -0.0000

Data Index: 968291 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 9.0413. Min Range: -9.0413

Max Act: 7.2950. Min Act: -0.0000

Data Index: 964625 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 9.0413. Min Range: -9.0413

Max Act: 7.4266. Min Act: -0.0000

Data Index: 1086399 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 9.0413. Min Range: -9.0413

Max Act: 7.2355. Min Act: -0.0000

Data Index: 317242 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 9.0413. Min Range: -9.0413

Max Act: 7.0810. Min Act: -0.0000

Data Index: 271059 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 9.0413. Min Range: -9.0413

Max Act: 6.6679. Min Act: -0.0000

Data Index: 575702 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 9.0413. Min Range: -9.0413

Max Act: 6.5815. Min Act: -0.0000

Data Index: 729483 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 9.0413. Min Range: -9.0413

Max Act: 6.7006. Min Act: -0.0000

Data Index: 867394 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 9.0413. Min Range: -9.0413

Max Act: 6.6277. Min Act: -0.0000

Data Index: 683120 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 9.0413. Min Range: -9.0413

Max Act: 6.5821. Min Act: -0.0000

Data Index: 570617 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 9.0413. Min Range: -9.0413

Max Act: 6.3823. Min Act: -0.0000

Data Index: 975278 (C4 (Web Text))

Max Activating Token Index: 37