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

Dataset: The Pile

Neuron 467 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.9454. Min Act: -0.0000

Data Index: 626917 (The Pile)

Max Activating Token Index: 707

Text #1

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6971. Min Act: -0.0000

Data Index: 880505 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6453. Min Act: -0.0000

Data Index: 979870 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6318. Min Act: -0.0000

Data Index: 214684 (The Pile)

Max Activating Token Index: 669

Text #4

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1192980 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.5631. Min Act: -0.0000

Data Index: 840443 (The Pile)

Max Activating Token Index: 833

Text #6

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6897. Min Act: -0.0000

Data Index: 170891 (The Pile)

Max Activating Token Index: 1003

Text #7

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1923805 (The Pile)

Max Activating Token Index: 965

Text #8

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6351. Min Act: -0.0000

Data Index: 1342636 (The Pile)

Max Activating Token Index: 841

Text #9

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1120393 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6213. Min Act: -0.0000

Data Index: 955624 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.5644. Min Act: -0.0000

Data Index: 580829 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6050. Min Act: -0.0000

Data Index: 457479 (The Pile)

Max Activating Token Index: 449

Text #13

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1095192 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.5663. Min Act: -0.0000

Data Index: 421041 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.5697. Min Act: -0.0000

Data Index: 932119 (The Pile)

Max Activating Token Index: 388

Text #16

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.5593. Min Act: -0.0000

Data Index: 621963 (The Pile)

Max Activating Token Index: 589

Text #17

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1609821 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.5550. Min Act: -0.0000

Data Index: 414857 (The Pile)

Max Activating Token Index: 887

Text #19

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.5565. Min Act: -0.0000

Data Index: 512879 (The Pile)

Max Activating Token Index: 621