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

Dataset: The Pile

Neuron 1779 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1914734 (The Pile)

Max Activating Token Index: 946

Text #1

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.6332. Min Act: -0.0000

Data Index: 865698 (The Pile)

Max Activating Token Index: 532

Text #2

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1075273 (The Pile)

Max Activating Token Index: 371

Text #3

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1065330 (The Pile)

Max Activating Token Index: 690

Text #4

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.6416. Min Act: -0.0000

Data Index: 120343 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1332519 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5631. Min Act: -0.0000

Data Index: 452347 (The Pile)

Max Activating Token Index: 102

Text #7

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1547588 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1591250 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1891195 (The Pile)

Max Activating Token Index: 931

Text #10

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1175244 (The Pile)

Max Activating Token Index: 438

Text #11

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5355. Min Act: -0.0000

Data Index: 78502 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5325. Min Act: -0.0000

Data Index: 114106 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5164. Min Act: -0.0000

Data Index: 749154 (The Pile)

Max Activating Token Index: 590

Text #14

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5155. Min Act: -0.0000

Data Index: 383583 (The Pile)

Max Activating Token Index: 677

Text #15

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1039673 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5124. Min Act: -0.0000

Data Index: 253499 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5081. Min Act: -0.0000

Data Index: 515359 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.4956. Min Act: -0.0000

Data Index: 143295 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.4646. Min Act: -0.0000

Data Index: 720687 (The Pile)

Max Activating Token Index: 761