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

Dataset: The Pile

Neuron 4796 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7746. Min Act: -0.0000

Data Index: 38151 (The Pile)

Max Activating Token Index: 940

Text #1

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7787. Min Act: -0.0000

Data Index: 907731 (The Pile)

Max Activating Token Index: 35

Text #2

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1596340 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1822967 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1000790 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1146405 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7668. Min Act: -0.0000

Data Index: 803276 (The Pile)

Max Activating Token Index: 949

Text #7

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6824. Min Act: -0.0000

Data Index: 443063 (The Pile)

Max Activating Token Index: 459

Text #8

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6745. Min Act: -0.0000

Data Index: 883685 (The Pile)

Max Activating Token Index: 867

Text #9

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6874. Min Act: -0.0000

Data Index: 346189 (The Pile)

Max Activating Token Index: 836

Text #10

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7284. Min Act: -0.0000

Data Index: 612383 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7328. Min Act: -0.0000

Data Index: 515214 (The Pile)

Max Activating Token Index: 808

Text #12

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1006384 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6990. Min Act: -0.0000

Data Index: 905283 (The Pile)

Max Activating Token Index: 486

Text #14

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1847380 (The Pile)

Max Activating Token Index: 329

Text #15

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6302. Min Act: -0.0000

Data Index: 937304 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1742019 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6641. Min Act: -0.0000

Data Index: 609863 (The Pile)

Max Activating Token Index: 728

Text #18

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6338. Min Act: -0.0000

Data Index: 872697 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1201877 (The Pile)

Max Activating Token Index: 832