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

Dataset: The Pile

Neuron 4997 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: 0.9860. Min Range: -0.9860

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1465483 (The Pile)

Max Activating Token Index: 521

Text #1

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.9062. Min Act: -0.0000

Data Index: 447115 (The Pile)

Max Activating Token Index: 28

Text #2

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8431. Min Act: -0.0000

Data Index: 1109247 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1396778 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1768592 (The Pile)

Max Activating Token Index: 281

Text #5

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1291263 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1321915 (The Pile)

Max Activating Token Index: 158

Text #7

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1065087 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1618546 (The Pile)

Max Activating Token Index: 552

Text #9

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1097078 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.6127. Min Act: -0.0000

Data Index: 481615 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.5915. Min Act: -0.0000

Data Index: 750287 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1675910 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1461498 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.5791. Min Act: -0.0000

Data Index: 690703 (The Pile)

Max Activating Token Index: 821

Text #15

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.5795. Min Act: -0.0000

Data Index: 175048 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.5248. Min Act: -0.0000

Data Index: 857092 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1574842 (The Pile)

Max Activating Token Index: 841

Text #18

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1253608 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.5879. Min Act: -0.0000

Data Index: 666387 (The Pile)

Max Activating Token Index: 720