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

Dataset: The Pile

Neuron 1674 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7483. Min Range: -5.7483

Max Act: 5.7483. Min Act: -0.0000

Data Index: 292402 (The Pile)

Max Activating Token Index: 649

Text #1

Max Range: 5.7483. Min Range: -5.7483

Max Act: 5.2038. Min Act: -0.0000

Data Index: 1933648 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 5.7483. Min Range: -5.7483

Max Act: 4.6474. Min Act: -0.0000

Data Index: 1976945 (The Pile)

Max Activating Token Index: 5

Text #3

Max Range: 5.7483. Min Range: -5.7483

Max Act: 4.4908. Min Act: -0.0000

Data Index: 55238 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 5.7483. Min Range: -5.7483

Max Act: 4.5356. Min Act: -0.0000

Data Index: 250233 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 5.7483. Min Range: -5.7483

Max Act: 4.4499. Min Act: -0.0000

Data Index: 1451071 (The Pile)

Max Activating Token Index: 675

Text #6

Max Range: 5.7483. Min Range: -5.7483

Max Act: 4.2383. Min Act: -0.0000

Data Index: 1169529 (The Pile)

Max Activating Token Index: 897

Text #7

Max Range: 5.7483. Min Range: -5.7483

Max Act: 4.0229. Min Act: -0.0000

Data Index: 1998924 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 5.7483. Min Range: -5.7483

Max Act: 4.1645. Min Act: -0.0000

Data Index: 745184 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 5.7483. Min Range: -5.7483

Max Act: 4.0326. Min Act: -0.0000

Data Index: 23705 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 5.7483. Min Range: -5.7483

Max Act: 4.0495. Min Act: -0.0000

Data Index: 1600488 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 5.7483. Min Range: -5.7483

Max Act: 3.9308. Min Act: -0.0000

Data Index: 1114909 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 5.7483. Min Range: -5.7483

Max Act: 3.7203. Min Act: -0.0000

Data Index: 700954 (The Pile)

Max Activating Token Index: 604

Text #13

Max Range: 5.7483. Min Range: -5.7483

Max Act: 3.7049. Min Act: -0.0000

Data Index: 1368817 (The Pile)

Max Activating Token Index: 361

Text #14

Max Range: 5.7483. Min Range: -5.7483

Max Act: 3.4975. Min Act: -0.0000

Data Index: 420758 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 5.7483. Min Range: -5.7483

Max Act: 3.9162. Min Act: -0.0000

Data Index: 1161654 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 5.7483. Min Range: -5.7483

Max Act: 3.7371. Min Act: -0.0000

Data Index: 1648628 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 5.7483. Min Range: -5.7483

Max Act: 3.8845. Min Act: -0.0000

Data Index: 759785 (The Pile)

Max Activating Token Index: 426

Text #18

Max Range: 5.7483. Min Range: -5.7483

Max Act: 3.6394. Min Act: -0.0000

Data Index: 1023961 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 5.7483. Min Range: -5.7483

Max Act: 3.8164. Min Act: -0.0000

Data Index: 165953 (The Pile)

Max Activating Token Index: 992