Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3763 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.5814. Min Act: -0.0000

Data Index: 1346974 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.4771. Min Act: -0.0000

Data Index: 232446 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.2816. Min Act: -0.0000

Data Index: 708869 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.2447. Min Act: -0.0000

Data Index: 642528 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.3382. Min Act: -0.0000

Data Index: 650551 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.4036. Min Act: -0.0000

Data Index: 786323 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.3450. Min Act: -0.0000

Data Index: 1591698 (Python Code)

Max Activating Token Index: 396

Text #7

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.3058. Min Act: -0.0000

Data Index: 1345638 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.2196. Min Act: -0.0000

Data Index: 165506 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.3025. Min Act: -0.0000

Data Index: 169663 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.3279. Min Act: -0.0000

Data Index: 388334 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1275616 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.1820. Min Act: -0.0000

Data Index: 191286 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.1887. Min Act: -0.0000

Data Index: 526199 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.1327. Min Act: -0.0000

Data Index: 209751 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.0729. Min Act: -0.0000

Data Index: 875587 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.1251. Min Act: -0.0000

Data Index: 187895 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1629701 (Python Code)

Max Activating Token Index: 610

Text #18

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.1130. Min Act: -0.0000

Data Index: 529209 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 1.5814. Min Range: -1.5814

Max Act: 1.0344. Min Act: -0.0000

Data Index: 243875 (C4 (Web Text))

Max Activating Token Index: 672