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

Dataset: The Pile

Neuron 384 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: 0.5228. Min Range: -0.5228

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1526781 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1077187 (The Pile)

Max Activating Token Index: 439

Text #2

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3580. Min Act: -0.0000

Data Index: 760404 (The Pile)

Max Activating Token Index: 357

Text #3

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1960797 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1626724 (The Pile)

Max Activating Token Index: 346

Text #5

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1209986 (The Pile)

Max Activating Token Index: 335

Text #6

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1372083 (The Pile)

Max Activating Token Index: 853

Text #7

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3015. Min Act: -0.0000

Data Index: 19818 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1149821 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1859469 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.2799. Min Act: -0.0000

Data Index: 527190 (The Pile)

Max Activating Token Index: 764

Text #11

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1723059 (The Pile)

Max Activating Token Index: 166

Text #12

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1156194 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1782949 (The Pile)

Max Activating Token Index: 621

Text #14

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.2498. Min Act: -0.0000

Data Index: 865537 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1214307 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.2615. Min Act: -0.0000

Data Index: 628142 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1352037 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.2407. Min Act: -0.0000

Data Index: 656030 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1518027 (The Pile)

Max Activating Token Index: 107