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

Dataset: The Pile

Neuron 371 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0105. Min Range: -1.0105

Max Act: 1.0105. Min Act: -0.0000

Data Index: 1331651 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8544. Min Act: -0.0000

Data Index: 440812 (The Pile)

Max Activating Token Index: 176

Text #2

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.9132. Min Act: -0.0000

Data Index: 907899 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8997. Min Act: -0.0000

Data Index: 477728 (The Pile)

Max Activating Token Index: 214

Text #4

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8359. Min Act: -0.0000

Data Index: 264289 (The Pile)

Max Activating Token Index: 513

Text #5

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8398. Min Act: -0.0000

Data Index: 453532 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8526. Min Act: -0.0000

Data Index: 930493 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1900244 (The Pile)

Max Activating Token Index: 301

Text #8

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1124027 (The Pile)

Max Activating Token Index: 554

Text #9

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1694883 (The Pile)

Max Activating Token Index: 434

Text #10

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1537938 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1766239 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7479. Min Act: -0.0000

Data Index: 195916 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7368. Min Act: -0.0000

Data Index: 422577 (The Pile)

Max Activating Token Index: 802

Text #14

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1417564 (The Pile)

Max Activating Token Index: 568

Text #15

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6875. Min Act: -0.0000

Data Index: 217699 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1312472 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1471750 (The Pile)

Max Activating Token Index: 728

Text #18

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1418407 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1922972 (The Pile)

Max Activating Token Index: 235