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

Dataset: The Pile

Neuron 5012 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: 1.7413. Min Range: -1.7413

Max Act: 1.7413. Min Act: -0.0000

Data Index: 1078183 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.5123. Min Act: -0.0000

Data Index: 1594538 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.2949. Min Act: -0.0000

Data Index: 1287138 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.2174. Min Act: -0.0000

Data Index: 708130 (The Pile)

Max Activating Token Index: 601

Text #4

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.2264. Min Act: -0.0000

Data Index: 687849 (The Pile)

Max Activating Token Index: 965

Text #5

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.2020. Min Act: -0.0001

Data Index: 140458 (The Pile)

Max Activating Token Index: 869

Text #6

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1048753 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.0649. Min Act: -0.0001

Data Index: 1259622 (The Pile)

Max Activating Token Index: 717

Text #8

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.2423. Min Act: -0.0000

Data Index: 583253 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.1828. Min Act: -0.0000

Data Index: 1658256 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.0468. Min Act: -0.0000

Data Index: 412973 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1933650 (The Pile)

Max Activating Token Index: 824

Text #12

Max Range: 1.7413. Min Range: -1.7413

Max Act: 0.9588. Min Act: -0.0001

Data Index: 1395449 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.1947. Min Act: -0.0000

Data Index: 439168 (The Pile)

Max Activating Token Index: 378

Text #14

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1371662 (The Pile)

Max Activating Token Index: 855

Text #15

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.0140. Min Act: -0.0001

Data Index: 489492 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.0645. Min Act: -0.0000

Data Index: 1030027 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1288728 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.1019. Min Act: -0.0000

Data Index: 1692469 (The Pile)

Max Activating Token Index: 975

Text #19

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.0708. Min Act: -0.0001

Data Index: 549768 (The Pile)

Max Activating Token Index: 561