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

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

Neuron 5057 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2812. Min Act: -0.0001

Data Index: 564560 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2101. Min Act: -0.0001

Data Index: 743529 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2358. Min Act: -0.0001

Data Index: 1118001 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2522. Min Act: -0.0001

Data Index: 403555 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2217. Min Act: -0.0001

Data Index: 100961 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1910. Min Act: -0.0001

Data Index: 7685 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1971. Min Act: -0.0001

Data Index: 802013 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2065. Min Act: -0.0001

Data Index: 823845 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1186715 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1872. Min Act: -0.0001

Data Index: 808649 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1649. Min Act: -0.0001

Data Index: 295651 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1663. Min Act: -0.0001

Data Index: 75985 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1997. Min Act: -0.0001

Data Index: 142487 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1115166 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1571. Min Act: -0.0001

Data Index: 81315 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1419. Min Act: -0.0001

Data Index: 235134 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1563. Min Act: -0.0001

Data Index: 932970 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1550. Min Act: -0.0001

Data Index: 732256 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1267. Min Act: -0.0001

Data Index: 230172 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1565. Min Act: -0.0001

Data Index: 130346 (C4 (Web Text))

Max Activating Token Index: 800