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

Dataset: The Pile

Neuron 4589 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.8934. Min Act: -0.0000

Data Index: 531139 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.3324. Min Act: -0.0000

Data Index: 1411199 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1142640 (The Pile)

Max Activating Token Index: 274

Text #3

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.0672. Min Act: -0.0000

Data Index: 1834159 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1341441 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.0262. Min Act: -0.0000

Data Index: 1326323 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.8974. Min Act: -0.0000

Data Index: 480463 (The Pile)

Max Activating Token Index: 833

Text #7

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.8967. Min Act: -0.0000

Data Index: 291964 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.9201. Min Act: -0.0000

Data Index: 1923321 (The Pile)

Max Activating Token Index: 865

Text #9

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.9508. Min Act: -0.0000

Data Index: 152190 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.9018. Min Act: -0.0000

Data Index: 979384 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.9389. Min Act: -0.0000

Data Index: 746241 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1167640 (The Pile)

Max Activating Token Index: 919

Text #13

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.9457. Min Act: -0.0000

Data Index: 436125 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1571264 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.8706. Min Act: -0.0000

Data Index: 104461 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.8422. Min Act: -0.0000

Data Index: 118882 (The Pile)

Max Activating Token Index: 491

Text #17

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1249340 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.8776. Min Act: -0.0000

Data Index: 6812 (The Pile)

Max Activating Token Index: 98

Text #19

Max Range: 1.8934. Min Range: -1.8934

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1425815 (The Pile)

Max Activating Token Index: 857