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

Dataset: The Pile

Neuron 722 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2640. Min Act: -0.0000

Data Index: 260696 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2728. Min Act: -0.0000

Data Index: 701899 (The Pile)

Max Activating Token Index: 880

Text #2

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1022607 (The Pile)

Max Activating Token Index: 620

Text #3

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2523. Min Act: -0.0000

Data Index: 914072 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1751493 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1707852 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2137. Min Act: -0.0000

Data Index: 805071 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2058. Min Act: -0.0000

Data Index: 548290 (The Pile)

Max Activating Token Index: 751

Text #8

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2119. Min Act: -0.0000

Data Index: 117373 (The Pile)

Max Activating Token Index: 703

Text #9

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2089. Min Act: -0.0000

Data Index: 257985 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1807071 (The Pile)

Max Activating Token Index: 394

Text #11

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1846537 (The Pile)

Max Activating Token Index: 713

Text #12

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1879. Min Act: -0.0000

Data Index: 1669018 (The Pile)

Max Activating Token Index: 717

Text #13

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1808. Min Act: -0.0000

Data Index: 769066 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1751. Min Act: -0.0000

Data Index: 683306 (The Pile)

Max Activating Token Index: 378

Text #15

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1678. Min Act: -0.0000

Data Index: 769362 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1675. Min Act: -0.0000

Data Index: 1214112 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1683. Min Act: -0.0000

Data Index: 413795 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1850951 (The Pile)

Max Activating Token Index: 917

Text #19

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1059164 (The Pile)

Max Activating Token Index: 374