Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3841 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8947. Min Act: -0.0001

Data Index: 488696 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 1.1016. Min Range: -1.1016

Max Act: 1.1016. Min Act: -0.0001

Data Index: 1959653 (The Pile)

Max Activating Token Index: 11

Text #2

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8577. Min Act: -0.0001

Data Index: 1131620 (The Pile)

Max Activating Token Index: 35

Text #3

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8703. Min Act: -0.0001

Data Index: 1254010 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8134. Min Act: -0.0001

Data Index: 355323 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8352. Min Act: -0.0001

Data Index: 982378 (The Pile)

Max Activating Token Index: 997

Text #6

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8452. Min Act: -0.0001

Data Index: 1713461 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8174. Min Act: -0.0001

Data Index: 1279484 (The Pile)

Max Activating Token Index: 23

Text #8

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.9144. Min Act: -0.0001

Data Index: 715244 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7965. Min Act: -0.0001

Data Index: 1382952 (The Pile)

Max Activating Token Index: 10

Text #10

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8804. Min Act: -0.0001

Data Index: 1259767 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7620. Min Act: -0.0001

Data Index: 625416 (The Pile)

Max Activating Token Index: 762

Text #12

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7850. Min Act: -0.0001

Data Index: 460554 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7310. Min Act: -0.0001

Data Index: 9884 (The Pile)

Max Activating Token Index: 910

Text #14

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8743. Min Act: -0.0001

Data Index: 1291839 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8574. Min Act: -0.0001

Data Index: 1479236 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8785. Min Act: -0.0001

Data Index: 123984 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.5893. Min Act: -0.0001

Data Index: 1302019 (The Pile)

Max Activating Token Index: 508

Text #18

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8250. Min Act: -0.0001

Data Index: 854480 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8013. Min Act: -0.0001

Data Index: 1924905 (The Pile)

Max Activating Token Index: 897