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

Dataset: The Pile

Neuron 3218 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2402. Min Act: -0.0000

Data Index: 494498 (The Pile)

Max Activating Token Index: 824

Text #1

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1001008 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1350095 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1901. Min Act: -0.0000

Data Index: 1019896 (The Pile)

Max Activating Token Index: 901

Text #4

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1807. Min Act: -0.0000

Data Index: 544892 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1658. Min Act: -0.0000

Data Index: 682952 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1481588 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1147775 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1010760 (The Pile)

Max Activating Token Index: 405

Text #9

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1378297 (The Pile)

Max Activating Token Index: 734

Text #10

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1294557 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1605. Min Act: -0.0000

Data Index: 347153 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1645. Min Act: -0.0000

Data Index: 148906 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1414. Min Act: -0.0000

Data Index: 382100 (The Pile)

Max Activating Token Index: 802

Text #14

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1472. Min Act: -0.0000

Data Index: 749701 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1537. Min Act: -0.0000

Data Index: 521771 (The Pile)

Max Activating Token Index: 999

Text #16

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1424. Min Act: -0.0000

Data Index: 833216 (The Pile)

Max Activating Token Index: 642

Text #17

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1214. Min Act: -0.0000

Data Index: 543278 (The Pile)

Max Activating Token Index: 861

Text #18

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1516. Min Act: -0.0000

Data Index: 973003 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 0.2597. Min Range: -0.2597

Max Act: 0.1490. Min Act: -0.0000

Data Index: 730026 (The Pile)

Max Activating Token Index: 1021