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

Dataset: The Pile

Neuron 2222 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: 1.3244. Min Range: -1.3244

Max Act: 1.3244. Min Act: -0.0000

Data Index: 984875 (The Pile)

Max Activating Token Index: 805

Text #1

Max Range: 1.3244. Min Range: -1.3244

Max Act: 1.2374. Min Act: -0.0000

Data Index: 610670 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 1.3244. Min Range: -1.3244

Max Act: 1.2395. Min Act: -0.0000

Data Index: 409424 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 1.3244. Min Range: -1.3244

Max Act: 1.0983. Min Act: -0.0000

Data Index: 929437 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 1.3244. Min Range: -1.3244

Max Act: 1.0164. Min Act: -0.0000

Data Index: 1830076 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1097891 (The Pile)

Max Activating Token Index: 675

Text #6

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1677714 (The Pile)

Max Activating Token Index: 224

Text #7

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8924. Min Act: -0.0000

Data Index: 137856 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8366. Min Act: -0.0000

Data Index: 236654 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8543. Min Act: -0.0000

Data Index: 212877 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1029696 (The Pile)

Max Activating Token Index: 619

Text #11

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8176. Min Act: -0.0000

Data Index: 964747 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8742. Min Act: -0.0000

Data Index: 283558 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1878753 (The Pile)

Max Activating Token Index: 725

Text #14

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.9523. Min Act: -0.0000

Data Index: 230363 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1490128 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1234543 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8201. Min Act: -0.0000

Data Index: 900828 (The Pile)

Max Activating Token Index: 609

Text #18

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1985381 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8121. Min Act: -0.0000

Data Index: 545793 (The Pile)

Max Activating Token Index: 993