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

Dataset: The Pile

Neuron 4797 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6768. Min Act: 0.0000

Data Index: 630052 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5475. Min Act: -0.0000

Data Index: 480478 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1090132 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5485. Min Act: -0.0000

Data Index: 354987 (The Pile)

Max Activating Token Index: 75

Text #4

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1479171 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1682776 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1769379 (The Pile)

Max Activating Token Index: 602

Text #7

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1258846 (The Pile)

Max Activating Token Index: 392

Text #8

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1145489 (The Pile)

Max Activating Token Index: 148

Text #9

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1991798 (The Pile)

Max Activating Token Index: 616

Text #10

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5077. Min Act: -0.0000

Data Index: 312351 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5224. Min Act: -0.0000

Data Index: 99689 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1053926 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1728504 (The Pile)

Max Activating Token Index: 911

Text #14

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5212. Min Act: -0.0000

Data Index: 146836 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1110805 (The Pile)

Max Activating Token Index: 532

Text #16

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4744. Min Act: -0.0000

Data Index: 349722 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1243900 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5050. Min Act: -0.0000

Data Index: 319908 (The Pile)

Max Activating Token Index: 222

Text #19

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1419182 (The Pile)

Max Activating Token Index: 826