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

Dataset: The Pile

Neuron 2573 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: 7.6929. Min Range: -7.6929

Max Act: 7.6365. Min Act: -0.0000

Data Index: 1374614 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 7.6929. Min Range: -7.6929

Max Act: 7.6929. Min Act: -0.0000

Data Index: 1346178 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 7.6929. Min Range: -7.6929

Max Act: 7.3427. Min Act: -0.0000

Data Index: 1479021 (The Pile)

Max Activating Token Index: 580

Text #3

Max Range: 7.6929. Min Range: -7.6929

Max Act: 7.2195. Min Act: -0.0000

Data Index: 1373980 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.9305. Min Act: -0.0000

Data Index: 757296 (The Pile)

Max Activating Token Index: 658

Text #5

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.8295. Min Act: -0.0000

Data Index: 929874 (The Pile)

Max Activating Token Index: 247

Text #6

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.4648. Min Act: -0.0000

Data Index: 1103496 (The Pile)

Max Activating Token Index: 426

Text #7

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.6152. Min Act: -0.0000

Data Index: 447174 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.7506. Min Act: -0.0000

Data Index: 1649350 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.8718. Min Act: -0.0000

Data Index: 676582 (The Pile)

Max Activating Token Index: 800

Text #10

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.6146. Min Act: -0.0000

Data Index: 1323777 (The Pile)

Max Activating Token Index: 1001

Text #11

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.5314. Min Act: -0.0000

Data Index: 325882 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.2648. Min Act: -0.0000

Data Index: 1396815 (The Pile)

Max Activating Token Index: 807

Text #13

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.2385. Min Act: -0.0000

Data Index: 635129 (The Pile)

Max Activating Token Index: 608

Text #14

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.4235. Min Act: -0.0000

Data Index: 27585 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 7.6929. Min Range: -7.6929

Max Act: 7.1593. Min Act: -0.0000

Data Index: 408435 (The Pile)

Max Activating Token Index: 590

Text #16

Max Range: 7.6929. Min Range: -7.6929

Max Act: 5.0563. Min Act: -0.0000

Data Index: 337205 (The Pile)

Max Activating Token Index: 844

Text #17

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.4783. Min Act: -0.0000

Data Index: 729080 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 7.6929. Min Range: -7.6929

Max Act: 5.7420. Min Act: -0.0000

Data Index: 1565276 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 7.6929. Min Range: -7.6929

Max Act: 6.0534. Min Act: -0.0000

Data Index: 17789 (The Pile)

Max Activating Token Index: 294