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

Dataset: The Pile

Neuron 4607 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: 1.0906. Min Range: -1.0906

Max Act: 1.0906. Min Act: -0.0000

Data Index: 1542876 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1210233 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9755. Min Act: -0.0000

Data Index: 508716 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9530. Min Act: -0.0000

Data Index: 602551 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1424989 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8443. Min Act: -0.0000

Data Index: 722637 (The Pile)

Max Activating Token Index: 287

Text #6

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1184085 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1760819 (The Pile)

Max Activating Token Index: 571

Text #8

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1997644 (The Pile)

Max Activating Token Index: 878

Text #9

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8190. Min Act: -0.0000

Data Index: 514166 (The Pile)

Max Activating Token Index: 566

Text #10

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8472. Min Act: -0.0000

Data Index: 100826 (The Pile)

Max Activating Token Index: 750

Text #11

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1866513 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8320. Min Act: -0.0000

Data Index: 30905 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.7517. Min Act: -0.0000

Data Index: 766920 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8501. Min Act: -0.0000

Data Index: 157979 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1047026 (The Pile)

Max Activating Token Index: 1018

Text #16

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8521. Min Act: -0.0000

Data Index: 33156 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1116993 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8515. Min Act: -0.0000

Data Index: 1278828 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1917158 (The Pile)

Max Activating Token Index: 473