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

Dataset: The Pile

Neuron 981 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: 1.0756. Min Range: -1.0756

Max Act: 1.0680. Min Act: -0.0000

Data Index: 614833 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 1.0756. Min Range: -1.0756

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1282569 (The Pile)

Max Activating Token Index: 945

Text #2

Max Range: 1.0756. Min Range: -1.0756

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1823225 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1488049 (The Pile)

Max Activating Token Index: 58

Text #4

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1741041 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8986. Min Act: -0.0000

Data Index: 812534 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8709. Min Act: -0.0000

Data Index: 1180321 (The Pile)

Max Activating Token Index: 143

Text #7

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9497. Min Act: -0.0000

Data Index: 287635 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9049. Min Act: -0.0000

Data Index: 314872 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1338089 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1076285 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8778. Min Act: -0.0000

Data Index: 321163 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8821. Min Act: -0.0000

Data Index: 109175 (The Pile)

Max Activating Token Index: 525

Text #13

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1256684 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1600257 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1960161 (The Pile)

Max Activating Token Index: 872

Text #16

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1337922 (The Pile)

Max Activating Token Index: 976

Text #17

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7468. Min Act: -0.0000

Data Index: 989304 (The Pile)

Max Activating Token Index: 291

Text #18

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7528. Min Act: -0.0000

Data Index: 19496 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7010. Min Act: -0.0000

Data Index: 890267 (The Pile)

Max Activating Token Index: 879