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

Dataset: The Pile

Neuron 2845 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: 1.4675. Min Range: -1.4675

Max Act: 1.4675. Min Act: -0.0000

Data Index: 28245 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.4401. Min Act: -0.0000

Data Index: 1086605 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.4554. Min Act: -0.0000

Data Index: 647157 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.3162. Min Act: -0.0000

Data Index: 531408 (The Pile)

Max Activating Token Index: 799

Text #4

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1651136 (The Pile)

Max Activating Token Index: 245

Text #5

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.4288. Min Act: -0.0000

Data Index: 776799 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.4177. Min Act: -0.0000

Data Index: 1906659 (The Pile)

Max Activating Token Index: 876

Text #7

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.2891. Min Act: -0.0000

Data Index: 408084 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.2697. Min Act: -0.0000

Data Index: 973735 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.2804. Min Act: -0.0000

Data Index: 893965 (The Pile)

Max Activating Token Index: 838

Text #10

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.2737. Min Act: -0.0000

Data Index: 500469 (The Pile)

Max Activating Token Index: 974

Text #11

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.2426. Min Act: -0.0000

Data Index: 932403 (The Pile)

Max Activating Token Index: 892

Text #12

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.1786. Min Act: -0.0000

Data Index: 1504377 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1823505 (The Pile)

Max Activating Token Index: 873

Text #14

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.3345. Min Act: -0.0000

Data Index: 662724 (The Pile)

Max Activating Token Index: 639

Text #15

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.2659. Min Act: -0.0000

Data Index: 958706 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.2644. Min Act: -0.0000

Data Index: 648940 (The Pile)

Max Activating Token Index: 659

Text #17

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1016075 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1005030 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 1.4675. Min Range: -1.4675

Max Act: 1.2317. Min Act: -0.0000

Data Index: 1156394 (The Pile)

Max Activating Token Index: 453