Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 119 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.4880. Min Act: -0.0000

Data Index: 519408 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.4181. Min Act: -0.0000

Data Index: 1381524 (The Pile)

Max Activating Token Index: 981

Text #2

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.4590. Min Act: -0.0000

Data Index: 51646 (The Pile)

Max Activating Token Index: 959

Text #3

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.3039. Min Act: -0.0000

Data Index: 859378 (The Pile)

Max Activating Token Index: 129

Text #4

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.4073. Min Act: -0.0000

Data Index: 1111151 (The Pile)

Max Activating Token Index: 557

Text #5

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.1927. Min Act: -0.0000

Data Index: 822108 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.1665. Min Act: -0.0000

Data Index: 906963 (The Pile)

Max Activating Token Index: 353

Text #7

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.1616. Min Act: -0.0000

Data Index: 404806 (The Pile)

Max Activating Token Index: 806

Text #8

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.1135. Min Act: -0.0000

Data Index: 1217909 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.1047. Min Act: -0.0000

Data Index: 1399322 (The Pile)

Max Activating Token Index: 864

Text #10

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.8832. Min Act: -0.0000

Data Index: 1771909 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.1391. Min Act: -0.0000

Data Index: 193125 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.8315. Min Act: -0.0000

Data Index: 1595212 (The Pile)

Max Activating Token Index: 407

Text #13

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.9712. Min Act: -0.0000

Data Index: 998817 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.9485. Min Act: -0.0000

Data Index: 1451703 (The Pile)

Max Activating Token Index: 529

Text #15

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.9493. Min Act: -0.0000

Data Index: 820189 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.8745. Min Act: -0.0000

Data Index: 1877103 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.9992. Min Act: -0.0000

Data Index: 494257 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.7269. Min Act: -0.0000

Data Index: 725080 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.9752. Min Act: -0.0000

Data Index: 291424 (The Pile)

Max Activating Token Index: 415