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

Dataset: The Pile

Neuron 33 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.6674. Min Act: -0.0000

Data Index: 662454 (The Pile)

Max Activating Token Index: 233

Text #1

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.5550. Min Act: -0.0000

Data Index: 911779 (The Pile)

Max Activating Token Index: 333

Text #2

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.5342. Min Act: -0.0000

Data Index: 1729354 (The Pile)

Max Activating Token Index: 634

Text #3

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.5199. Min Act: -0.0000

Data Index: 1148232 (The Pile)

Max Activating Token Index: 545

Text #4

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4837. Min Act: -0.0000

Data Index: 450412 (The Pile)

Max Activating Token Index: 18

Text #5

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4801. Min Act: -0.0000

Data Index: 447073 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3903. Min Act: -0.0000

Data Index: 1269513 (The Pile)

Max Activating Token Index: 182

Text #7

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4603. Min Act: -0.0000

Data Index: 732320 (The Pile)

Max Activating Token Index: 768

Text #8

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4595. Min Act: -0.0000

Data Index: 1424605 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4562. Min Act: -0.0000

Data Index: 536425 (The Pile)

Max Activating Token Index: 233

Text #10

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3641. Min Act: -0.0000

Data Index: 1271104 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4461. Min Act: -0.0000

Data Index: 199273 (The Pile)

Max Activating Token Index: 273

Text #12

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3334. Min Act: -0.0000

Data Index: 428646 (The Pile)

Max Activating Token Index: 513

Text #13

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4017. Min Act: -0.0000

Data Index: 770081 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3018. Min Act: -0.0000

Data Index: 1022668 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3643. Min Act: -0.0000

Data Index: 39290 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3567. Min Act: -0.0000

Data Index: 1417996 (The Pile)

Max Activating Token Index: 403

Text #17

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3624. Min Act: -0.0000

Data Index: 170736 (The Pile)

Max Activating Token Index: 447

Text #18

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4286. Min Act: -0.0000

Data Index: 1097187 (The Pile)

Max Activating Token Index: 82

Text #19

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.2568. Min Act: -0.0000

Data Index: 329668 (The Pile)

Max Activating Token Index: 677