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

Dataset: The Pile

Neuron 2245 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: 1.6617. Min Range: -1.6617

Max Act: 1.5950. Min Act: -0.0000

Data Index: 1043531 (The Pile)

Max Activating Token Index: 550

Text #1

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.6617. Min Act: -0.0000

Data Index: 103634 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.5052. Min Act: -0.0000

Data Index: 1063118 (The Pile)

Max Activating Token Index: 712

Text #3

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.5811. Min Act: -0.0000

Data Index: 205070 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.5406. Min Act: -0.0000

Data Index: 1643746 (The Pile)

Max Activating Token Index: 240

Text #5

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.3625. Min Act: -0.0000

Data Index: 1397433 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4122. Min Act: -0.0000

Data Index: 539386 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.4731. Min Act: -0.0000

Data Index: 158587 (The Pile)

Max Activating Token Index: 458

Text #8

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.3710. Min Act: -0.0000

Data Index: 1636658 (The Pile)

Max Activating Token Index: 339

Text #9

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.2658. Min Act: -0.0000

Data Index: 684050 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.2642. Min Act: -0.0000

Data Index: 188595 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.2583. Min Act: -0.0000

Data Index: 1175444 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.3106. Min Act: -0.0000

Data Index: 1025835 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.2968. Min Act: 0.0000

Data Index: 384614 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.3014. Min Act: -0.0000

Data Index: 810440 (The Pile)

Max Activating Token Index: 676

Text #15

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.2935. Min Act: -0.0000

Data Index: 1414391 (The Pile)

Max Activating Token Index: 894

Text #16

Max Range: 1.6617. Min Range: -1.6617

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1876487 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.2391. Min Act: -0.0000

Data Index: 1759820 (The Pile)

Max Activating Token Index: 910

Text #18

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1994831 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 1.6617. Min Range: -1.6617

Max Act: 1.1758. Min Act: 0.0000

Data Index: 1824344 (The Pile)

Max Activating Token Index: 664