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

Dataset: The Pile

Neuron 2000 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1714495 (The Pile)

Max Activating Token Index: 905

Text #1

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7864. Min Act: -0.0000

Data Index: 707470 (The Pile)

Max Activating Token Index: 177

Text #2

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1513394 (The Pile)

Max Activating Token Index: 634

Text #3

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.8235. Min Act: -0.0000

Data Index: 1093717 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1388069 (The Pile)

Max Activating Token Index: 295

Text #5

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1058637 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1328251 (The Pile)

Max Activating Token Index: 828

Text #7

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1225368 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1592757 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1208594 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1643588 (The Pile)

Max Activating Token Index: 502

Text #11

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7640. Min Act: -0.0000

Data Index: 271511 (The Pile)

Max Activating Token Index: 334

Text #12

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1981122 (The Pile)

Max Activating Token Index: 983

Text #13

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6654. Min Act: -0.0000

Data Index: 261765 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6688. Min Act: -0.0000

Data Index: 954408 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1988609 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1009095 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1374222 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1624633 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1608291 (The Pile)

Max Activating Token Index: 146