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

Dataset: The Pile

Neuron 735 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: 0.6912. Min Range: -0.6912

Max Act: 0.6912. Min Act: -0.0000

Data Index: 352991 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1446803 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.6030. Min Act: -0.0000

Data Index: 172714 (The Pile)

Max Activating Token Index: 96

Text #3

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1105625 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5615. Min Act: -0.0000

Data Index: 16365 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1460615 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5182. Min Act: -0.0000

Data Index: 680788 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5382. Min Act: -0.0000

Data Index: 80225 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4762. Min Act: -0.0000

Data Index: 849966 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1386981 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1149121 (The Pile)

Max Activating Token Index: 208

Text #11

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1745143 (The Pile)

Max Activating Token Index: 762

Text #12

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5009. Min Act: -0.0000

Data Index: 670674 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5404. Min Act: -0.0000

Data Index: 1546340 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1164593 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1314793 (The Pile)

Max Activating Token Index: 417

Text #16

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1369798 (The Pile)

Max Activating Token Index: 858

Text #17

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4945. Min Act: -0.0000

Data Index: 114430 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4771. Min Act: -0.0000

Data Index: 939070 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4302. Min Act: -0.0000

Data Index: 476071 (The Pile)

Max Activating Token Index: 771