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

Dataset: The Pile

Neuron 3324 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.4353. Min Act: -0.0000

Data Index: 1752384 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.1126. Min Act: -0.0000

Data Index: 1275578 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.7133. Min Act: -0.0000

Data Index: 114267 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.1610. Min Act: -0.0000

Data Index: 342107 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.3449. Min Act: -0.0000

Data Index: 1871763 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.1886. Min Act: -0.0000

Data Index: 1331553 (The Pile)

Max Activating Token Index: 389

Text #6

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.1319. Min Act: -0.0000

Data Index: 860413 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.2408. Min Act: -0.0000

Data Index: 692679 (The Pile)

Max Activating Token Index: 338

Text #8

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.2463. Min Act: -0.0000

Data Index: 759920 (The Pile)

Max Activating Token Index: 358

Text #9

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.0860. Min Act: -0.0000

Data Index: 1057200 (The Pile)

Max Activating Token Index: 155

Text #10

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.1855. Min Act: 0.0000

Data Index: 1890542 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 3.7133. Min Range: -3.7133

Max Act: 2.8965. Min Act: -0.0000

Data Index: 1993955 (The Pile)

Max Activating Token Index: 509

Text #12

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.1699. Min Act: -0.0000

Data Index: 815124 (The Pile)

Max Activating Token Index: 396

Text #13

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.1427. Min Act: -0.0000

Data Index: 812601 (The Pile)

Max Activating Token Index: 535

Text #14

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.2819. Min Act: -0.0000

Data Index: 1425140 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.0880. Min Act: -0.0000

Data Index: 1887841 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.0865. Min Act: 0.0000

Data Index: 1594947 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 3.7133. Min Range: -3.7133

Max Act: 2.9274. Min Act: -0.0000

Data Index: 888102 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.1865. Min Act: -0.0000

Data Index: 417661 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 3.7133. Min Range: -3.7133

Max Act: 3.0434. Min Act: -0.0000

Data Index: 891553 (The Pile)

Max Activating Token Index: 952