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

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

Neuron 4878 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0598. Min Act: -0.0002

Data Index: 76439 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1630523 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1594305 (Python Code)

Max Activating Token Index: 17

Text #3

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1650202 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1538948 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1326403 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0476. Min Act: -0.0002

Data Index: 78043 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0476. Min Act: -0.0002

Data Index: 731733 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1424090 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0475. Min Act: -0.0002

Data Index: 20046 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0466. Min Act: -0.0002

Data Index: 213911 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1043455 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0478. Min Act: -0.0002

Data Index: 156821 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0454. Min Act: -0.0002

Data Index: 234692 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0436. Min Act: -0.0002

Data Index: 960417 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1213930 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1474520 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0430. Min Act: -0.0002

Data Index: 21362 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1591186 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0425. Min Act: -0.0002

Data Index: 980577 (C4 (Web Text))

Max Activating Token Index: 8