Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3357 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.5323. Min Act: -0.0000

Data Index: 1971633 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2448. Min Act: -0.0000

Data Index: 30883 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 3.5323. Min Range: -3.5323

Max Act: 2.9303. Min Act: -0.0000

Data Index: 1111392 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.1874. Min Act: -0.0000

Data Index: 1006397 (The Pile)

Max Activating Token Index: 290

Text #4

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.1126. Min Act: -0.0000

Data Index: 1667837 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 3.5323. Min Range: -3.5323

Max Act: 2.9687. Min Act: -0.0000

Data Index: 1824273 (The Pile)

Max Activating Token Index: 39

Text #6

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.1268. Min Act: -0.0000

Data Index: 475374 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.1004. Min Act: -0.0000

Data Index: 1514774 (The Pile)

Max Activating Token Index: 596

Text #8

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2386. Min Act: -0.0000

Data Index: 1344992 (The Pile)

Max Activating Token Index: 867

Text #9

Max Range: 3.5323. Min Range: -3.5323

Max Act: 2.7496. Min Act: -0.0000

Data Index: 1183513 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 3.5323. Min Range: -3.5323

Max Act: 2.7282. Min Act: -0.0000

Data Index: 439920 (The Pile)

Max Activating Token Index: 873

Text #11

Max Range: 3.5323. Min Range: -3.5323

Max Act: 2.8701. Min Act: -0.0000

Data Index: 1881751 (The Pile)

Max Activating Token Index: 892

Text #12

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0357. Min Act: -0.0000

Data Index: 203018 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 3.5323. Min Range: -3.5323

Max Act: 2.7973. Min Act: -0.0000

Data Index: 1252946 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 3.5323. Min Range: -3.5323

Max Act: 2.9717. Min Act: -0.0000

Data Index: 496058 (The Pile)

Max Activating Token Index: 279

Text #15

Max Range: 3.5323. Min Range: -3.5323

Max Act: 2.9403. Min Act: -0.0000

Data Index: 1902116 (The Pile)

Max Activating Token Index: 363

Text #16

Max Range: 3.5323. Min Range: -3.5323

Max Act: 2.8112. Min Act: -0.0000

Data Index: 1094044 (The Pile)

Max Activating Token Index: 191

Text #17

Max Range: 3.5323. Min Range: -3.5323

Max Act: 2.9340. Min Act: -0.0000

Data Index: 219839 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 3.5323. Min Range: -3.5323

Max Act: 2.6950. Min Act: -0.0000

Data Index: 1786345 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.0643. Min Act: -0.0000

Data Index: 1812658 (The Pile)

Max Activating Token Index: 63