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

Dataset: The Pile

Neuron 3373 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1670468 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8583. Min Act: -0.0000

Data Index: 930661 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1791519 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8650. Min Act: -0.0000

Data Index: 731677 (The Pile)

Max Activating Token Index: 659

Text #4

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1408304 (The Pile)

Max Activating Token Index: 724

Text #5

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1539498 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7565. Min Act: -0.0000

Data Index: 948865 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1911641 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7970. Min Act: -0.0000

Data Index: 289670 (The Pile)

Max Activating Token Index: 879

Text #9

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1321349 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1510196 (The Pile)

Max Activating Token Index: 646

Text #11

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1817935 (The Pile)

Max Activating Token Index: 487

Text #12

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1663974 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.6854. Min Act: -0.0000

Data Index: 966305 (The Pile)

Max Activating Token Index: 863

Text #14

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1811933 (The Pile)

Max Activating Token Index: 453

Text #15

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7786. Min Act: -0.0000

Data Index: 211455 (The Pile)

Max Activating Token Index: 768

Text #16

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7461. Min Act: -0.0000

Data Index: 333956 (The Pile)

Max Activating Token Index: 42

Text #17

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1683024 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.6050. Min Act: -0.0000

Data Index: 15530 (The Pile)

Max Activating Token Index: 668

Text #19

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.6812. Min Act: -0.0000

Data Index: 811015 (The Pile)

Max Activating Token Index: 770