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

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

Neuron 248 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: 1.9279. Min Range: -1.9279

Max Act: 1.8383. Min Act: -0.0001

Data Index: 727476 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.9279. Min Act: -0.0000

Data Index: 895115 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.7974. Min Act: -0.0001

Data Index: 764370 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.7838. Min Act: -0.0001

Data Index: 936071 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.7880. Min Act: -0.0001

Data Index: 297241 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.7863. Min Act: -0.0000

Data Index: 1131216 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8578. Min Act: -0.0001

Data Index: 53744 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.6543. Min Act: -0.0001

Data Index: 207906 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.6990. Min Act: -0.0000

Data Index: 632813 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.6949. Min Act: -0.0000

Data Index: 36443 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.6652. Min Act: -0.0001

Data Index: 692756 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.6966. Min Act: -0.0001

Data Index: 966450 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.5857. Min Act: -0.0000

Data Index: 1065844 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.6773. Min Act: -0.0001

Data Index: 390646 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.5897. Min Act: -0.0001

Data Index: 145178 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.5047. Min Act: -0.0001

Data Index: 505507 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.5574. Min Act: -0.0000

Data Index: 1347509 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.3925. Min Act: -0.0001

Data Index: 632626 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.4493. Min Act: -0.0001

Data Index: 1114832 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.5181. Min Act: -0.0000

Data Index: 598571 (C4 (Web Text))

Max Activating Token Index: 475