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

Dataset: The Pile

Neuron 2938 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: 1.9131. Min Range: -1.9131

Max Act: 1.8598. Min Act: -0.0000

Data Index: 1484563 (The Pile)

Max Activating Token Index: 616

Text #1

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.9131. Min Act: -0.0000

Data Index: 515337 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.3893. Min Act: -0.0000

Data Index: 1214059 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.8424. Min Act: -0.0000

Data Index: 1447646 (The Pile)

Max Activating Token Index: 993

Text #4

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.5413. Min Act: -0.0000

Data Index: 829865 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.3464. Min Act: -0.0000

Data Index: 27432 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1755403 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.3993. Min Act: -0.0000

Data Index: 1408269 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.2529. Min Act: -0.0000

Data Index: 1528003 (The Pile)

Max Activating Token Index: 256

Text #9

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.3392. Min Act: -0.0000

Data Index: 683680 (The Pile)

Max Activating Token Index: 122

Text #10

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.2682. Min Act: -0.0000

Data Index: 132576 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.1819. Min Act: -0.0000

Data Index: 1341817 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.0788. Min Act: -0.0000

Data Index: 841612 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1775077 (The Pile)

Max Activating Token Index: 489

Text #14

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.1974. Min Act: -0.0001

Data Index: 138980 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.2499. Min Act: -0.0000

Data Index: 1502997 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.2083. Min Act: -0.0000

Data Index: 1326760 (The Pile)

Max Activating Token Index: 465

Text #17

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.1962. Min Act: -0.0000

Data Index: 1464497 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.2368. Min Act: -0.0000

Data Index: 1818488 (The Pile)

Max Activating Token Index: 122

Text #19

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.0886. Min Act: -0.0000

Data Index: 1829551 (The Pile)

Max Activating Token Index: 911