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

Dataset: The Pile

Neuron 4908 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: 5.1684. Min Range: -5.1684

Max Act: 4.9415. Min Act: 0.0000

Data Index: 427484 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 5.1684. Min Range: -5.1684

Max Act: 5.1684. Min Act: 0.0000

Data Index: 1704433 (The Pile)

Max Activating Token Index: 74

Text #2

Max Range: 5.1684. Min Range: -5.1684

Max Act: 4.6641. Min Act: -0.0000

Data Index: 1667391 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 5.1684. Min Range: -5.1684

Max Act: 4.4463. Min Act: -0.0000

Data Index: 24125 (The Pile)

Max Activating Token Index: 372

Text #4

Max Range: 5.1684. Min Range: -5.1684

Max Act: 3.9263. Min Act: -0.0000

Data Index: 1639740 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 5.1684. Min Range: -5.1684

Max Act: 3.4870. Min Act: -0.0000

Data Index: 1615410 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 5.1684. Min Range: -5.1684

Max Act: 3.6155. Min Act: -0.0000

Data Index: 128426 (The Pile)

Max Activating Token Index: 252

Text #7

Max Range: 5.1684. Min Range: -5.1684

Max Act: 3.7333. Min Act: -0.0000

Data Index: 67690 (The Pile)

Max Activating Token Index: 564

Text #8

Max Range: 5.1684. Min Range: -5.1684

Max Act: 3.3072. Min Act: -0.0000

Data Index: 844808 (The Pile)

Max Activating Token Index: 586

Text #9

Max Range: 5.1684. Min Range: -5.1684

Max Act: 3.2243. Min Act: -0.0000

Data Index: 287093 (The Pile)

Max Activating Token Index: 552

Text #10

Max Range: 5.1684. Min Range: -5.1684

Max Act: 3.0372. Min Act: -0.0000

Data Index: 1658448 (The Pile)

Max Activating Token Index: 364

Text #11

Max Range: 5.1684. Min Range: -5.1684

Max Act: 2.9933. Min Act: 0.0000

Data Index: 1488876 (The Pile)

Max Activating Token Index: 774

Text #12

Max Range: 5.1684. Min Range: -5.1684

Max Act: 2.8019. Min Act: -0.0000

Data Index: 764169 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 5.1684. Min Range: -5.1684

Max Act: 3.0639. Min Act: -0.0000

Data Index: 1600602 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 5.1684. Min Range: -5.1684

Max Act: 2.7584. Min Act: -0.0000

Data Index: 556566 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 5.1684. Min Range: -5.1684

Max Act: 3.0420. Min Act: -0.0000

Data Index: 591803 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 5.1684. Min Range: -5.1684

Max Act: 3.0125. Min Act: -0.0000

Data Index: 1630576 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 5.1684. Min Range: -5.1684

Max Act: 3.0007. Min Act: -0.0000

Data Index: 1924905 (The Pile)

Max Activating Token Index: 270

Text #18

Max Range: 5.1684. Min Range: -5.1684

Max Act: 2.6831. Min Act: -0.0000

Data Index: 1428214 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 5.1684. Min Range: -5.1684

Max Act: 2.7876. Min Act: -0.0000

Data Index: 187297 (The Pile)

Max Activating Token Index: 163