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

Dataset: The Pile

Neuron 2375 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: 1.0982. Min Range: -1.0982

Max Act: 1.0982. Min Act: -0.0000

Data Index: 1171921 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.8459. Min Act: -0.0000

Data Index: 1420003 (The Pile)

Max Activating Token Index: 3

Text #2

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.8281. Min Act: -0.0000

Data Index: 579399 (The Pile)

Max Activating Token Index: 5

Text #3

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7591. Min Act: -0.0000

Data Index: 700756 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7072. Min Act: -0.0000

Data Index: 268393 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.6873. Min Act: -0.0000

Data Index: 870085 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7573. Min Act: -0.0000

Data Index: 192209 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7858. Min Act: -0.0000

Data Index: 576967 (The Pile)

Max Activating Token Index: 525

Text #8

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7787. Min Act: -0.0000

Data Index: 106317 (The Pile)

Max Activating Token Index: 484

Text #9

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7305. Min Act: -0.0000

Data Index: 441297 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7526. Min Act: -0.0000

Data Index: 487270 (The Pile)

Max Activating Token Index: 5

Text #11

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7698. Min Act: -0.0000

Data Index: 890025 (The Pile)

Max Activating Token Index: 950

Text #12

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7366. Min Act: -0.0000

Data Index: 801488 (The Pile)

Max Activating Token Index: 50

Text #13

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7562. Min Act: -0.0000

Data Index: 260955 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7381. Min Act: -0.0000

Data Index: 675416 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1052146 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1438765 (The Pile)

Max Activating Token Index: 5

Text #17

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7251. Min Act: -0.0000

Data Index: 589112 (The Pile)

Max Activating Token Index: 53

Text #18

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1610584 (The Pile)

Max Activating Token Index: 45

Text #19

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1140592 (The Pile)

Max Activating Token Index: 601