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

Dataset: The Pile

Neuron 3788 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: 1.0570. Min Range: -1.0570

Max Act: 1.0570. Min Act: -0.0000

Data Index: 615831 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 1.0570. Min Range: -1.0570

Max Act: 1.0059. Min Act: -0.0000

Data Index: 32138 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7487. Min Act: -0.0000

Data Index: 408972 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.5771. Min Act: -0.0000

Data Index: 243257 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.5661. Min Act: -0.0000

Data Index: 363011 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.5375. Min Act: -0.0000

Data Index: 801701 (The Pile)

Max Activating Token Index: 713

Text #6

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.5792. Min Act: -0.0000

Data Index: 751479 (The Pile)

Max Activating Token Index: 390

Text #7

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1207380 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.4667. Min Act: -0.0000

Data Index: 820143 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1479187 (The Pile)

Max Activating Token Index: 144

Text #10

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.4502. Min Act: -0.0000

Data Index: 42632 (The Pile)

Max Activating Token Index: 697

Text #11

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1942624 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.4074. Min Act: -0.0000

Data Index: 757867 (The Pile)

Max Activating Token Index: 198

Text #13

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.3698. Min Act: -0.0000

Data Index: 262967 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.4061. Min Act: -0.0000

Data Index: 155296 (The Pile)

Max Activating Token Index: 72

Text #15

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1531386 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1473231 (The Pile)

Max Activating Token Index: 591

Text #17

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1278210 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1176687 (The Pile)

Max Activating Token Index: 733

Text #19

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.3437. Min Act: -0.0000

Data Index: 709136 (The Pile)

Max Activating Token Index: 161