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

Dataset: The Pile

Neuron 4591 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: 0.8538. Min Range: -0.8538

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1588346 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7890. Min Act: -0.0000

Data Index: 864418 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1205918 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7560. Min Act: -0.0000

Data Index: 1934301 (The Pile)

Max Activating Token Index: 339

Text #4

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7471. Min Act: -0.0000

Data Index: 519321 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7431. Min Act: -0.0001

Data Index: 1475925 (The Pile)

Max Activating Token Index: 556

Text #6

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7450. Min Act: -0.0000

Data Index: 643976 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1606661 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1847017 (The Pile)

Max Activating Token Index: 552

Text #9

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7523. Min Act: -0.0000

Data Index: 142537 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7597. Min Act: -0.0000

Data Index: 75213 (The Pile)

Max Activating Token Index: 428

Text #11

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7680. Min Act: -0.0000

Data Index: 82617 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1335135 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1185601 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7224. Min Act: -0.0000

Data Index: 112265 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7078. Min Act: -0.0000

Data Index: 668596 (The Pile)

Max Activating Token Index: 848

Text #16

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7621. Min Act: -0.0000

Data Index: 1819520 (The Pile)

Max Activating Token Index: 838

Text #17

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7288. Min Act: -0.0000

Data Index: 539463 (The Pile)

Max Activating Token Index: 69

Text #18

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7328. Min Act: -0.0000

Data Index: 377916 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7147. Min Act: -0.0000

Data Index: 866303 (The Pile)

Max Activating Token Index: 163