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

Dataset: The Pile

Neuron 648 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: 5.9957. Min Range: -5.9957

Max Act: 5.8911. Min Act: -0.0000

Data Index: 683347 (The Pile)

Max Activating Token Index: 550

Text #1

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.9957. Min Act: -0.0000

Data Index: 1534995 (The Pile)

Max Activating Token Index: 817

Text #2

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.9382. Min Act: -0.0000

Data Index: 1591816 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.9023. Min Act: -0.0000

Data Index: 948578 (The Pile)

Max Activating Token Index: 108

Text #4

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.8731. Min Act: -0.0000

Data Index: 858079 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.8463. Min Act: -0.0000

Data Index: 46944 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.8409. Min Act: -0.0000

Data Index: 1012497 (The Pile)

Max Activating Token Index: 486

Text #7

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.7368. Min Act: -0.0000

Data Index: 1256819 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.7305. Min Act: -0.0000

Data Index: 78395 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.7277. Min Act: -0.0000

Data Index: 614304 (The Pile)

Max Activating Token Index: 173

Text #10

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.3556. Min Act: -0.0000

Data Index: 962983 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.3558. Min Act: -0.0000

Data Index: 931959 (The Pile)

Max Activating Token Index: 294

Text #12

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.5316. Min Act: -0.0000

Data Index: 1155416 (The Pile)

Max Activating Token Index: 270

Text #13

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.8654. Min Act: -0.0000

Data Index: 808241 (The Pile)

Max Activating Token Index: 558

Text #14

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.6763. Min Act: -0.0000

Data Index: 1722450 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.4728. Min Act: -0.0000

Data Index: 143803 (The Pile)

Max Activating Token Index: 471

Text #16

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.6675. Min Act: -0.0000

Data Index: 499218 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.3025. Min Act: -0.0000

Data Index: 633548 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.4244. Min Act: -0.0000

Data Index: 290041 (The Pile)

Max Activating Token Index: 881

Text #19

Max Range: 5.9957. Min Range: -5.9957

Max Act: 5.3893. Min Act: -0.0000

Data Index: 1656424 (The Pile)

Max Activating Token Index: 327