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

Dataset: The Pile

Neuron 1591 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: 0.7962. Min Range: -0.7962

Max Act: 0.7962. Min Act: -0.0000

Data Index: 869098 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1534139 (The Pile)

Max Activating Token Index: 273

Text #2

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6095. Min Act: -0.0000

Data Index: 368417 (The Pile)

Max Activating Token Index: 158

Text #3

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1959851 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5918. Min Act: -0.0000

Data Index: 507821 (The Pile)

Max Activating Token Index: 109

Text #5

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5508. Min Act: -0.0000

Data Index: 707024 (The Pile)

Max Activating Token Index: 553

Text #6

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5704. Min Act: -0.0000

Data Index: 629970 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5420. Min Act: -0.0000

Data Index: 164424 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5252. Min Act: -0.0000

Data Index: 663662 (The Pile)

Max Activating Token Index: 919

Text #9

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1325408 (The Pile)

Max Activating Token Index: 475

Text #10

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1557086 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1339708 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1731637 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1191228 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.4877. Min Act: -0.0000

Data Index: 786368 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1968926 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1528431 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.4455. Min Act: -0.0000

Data Index: 165301 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1188867 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.4839. Min Act: -0.0000

Data Index: 324525 (The Pile)

Max Activating Token Index: 604