Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1136 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3974. Min Act: -0.0001

Data Index: 188341 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3638. Min Act: -0.0001

Data Index: 500924 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3620. Min Act: -0.0001

Data Index: 816463 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3723. Min Act: -0.0001

Data Index: 425947 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3688. Min Act: -0.0001

Data Index: 772664 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3574. Min Act: -0.0000

Data Index: 332043 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3450. Min Act: -0.0000

Data Index: 372571 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1223769 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3420. Min Act: -0.0001

Data Index: 488646 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3518. Min Act: -0.0001

Data Index: 489468 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3261. Min Act: -0.0001

Data Index: 1618765 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3146. Min Act: -0.0001

Data Index: 1299799 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3266. Min Act: -0.0001

Data Index: 819270 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3236. Min Act: -0.0001

Data Index: 63355 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3354. Min Act: -0.0001

Data Index: 878452 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3336. Min Act: -0.0001

Data Index: 1023900 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3219. Min Act: -0.0001

Data Index: 917289 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3372. Min Act: -0.0001

Data Index: 462711 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3243. Min Act: -0.0001

Data Index: 290959 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3164. Min Act: -0.0001

Data Index: 950088 (C4 (Web Text))

Max Activating Token Index: 326