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

Dataset: The Pile

Neuron 1222 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1700272 (The Pile)

Max Activating Token Index: 509

Text #1

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1760688 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5645. Min Act: -0.0000

Data Index: 780726 (The Pile)

Max Activating Token Index: 426

Text #3

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1088419 (The Pile)

Max Activating Token Index: 818

Text #4

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4954. Min Act: -0.0000

Data Index: 245378 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5151. Min Act: -0.0000

Data Index: 248630 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5061. Min Act: -0.0000

Data Index: 400560 (The Pile)

Max Activating Token Index: 494

Text #7

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4733. Min Act: -0.0000

Data Index: 158977 (The Pile)

Max Activating Token Index: 976

Text #8

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1475867 (The Pile)

Max Activating Token Index: 487

Text #9

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1408082 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1493527 (The Pile)

Max Activating Token Index: 386

Text #11

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4603. Min Act: -0.0000

Data Index: 534983 (The Pile)

Max Activating Token Index: 627

Text #12

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1661691 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1568083 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1751160 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4316. Min Act: -0.0000

Data Index: 623451 (The Pile)

Max Activating Token Index: 797

Text #16

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1914428 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1160196 (The Pile)

Max Activating Token Index: 201

Text #18

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4360. Min Act: -0.0000

Data Index: 446731 (The Pile)

Max Activating Token Index: 74

Text #19

Max Range: 0.5747. Min Range: -0.5747

Max Act: 0.4277. Min Act: -0.0000

Data Index: 348284 (The Pile)

Max Activating Token Index: 533