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

Dataset: The Pile

Neuron 3842 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: 0.8747. Min Range: -0.8747

Max Act: 0.7557. Min Act: -0.0000

Data Index: 743257 (The Pile)

Max Activating Token Index: 922

Text #1

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.8177. Min Act: -0.0000

Data Index: 983403 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1099600 (The Pile)

Max Activating Token Index: 861

Text #3

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1995331 (The Pile)

Max Activating Token Index: 761

Text #4

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1534339 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1894152 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7676. Min Act: -0.0000

Data Index: 756247 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7839. Min Act: -0.0000

Data Index: 486005 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.8522. Min Act: -0.0000

Data Index: 819573 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1653408 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1617901 (The Pile)

Max Activating Token Index: 682

Text #11

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.8747. Min Act: -0.0000

Data Index: 610144 (The Pile)

Max Activating Token Index: 923

Text #12

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1385567 (The Pile)

Max Activating Token Index: 797

Text #13

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1211091 (The Pile)

Max Activating Token Index: 569

Text #14

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.8296. Min Act: -0.0000

Data Index: 650263 (The Pile)

Max Activating Token Index: 849

Text #15

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7681. Min Act: -0.0000

Data Index: 289421 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1177954 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1393604 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7778. Min Act: -0.0000

Data Index: 827755 (The Pile)

Max Activating Token Index: 874

Text #19

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7566. Min Act: -0.0000

Data Index: 906435 (The Pile)

Max Activating Token Index: 541