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

Dataset: The Pile

Neuron 3115 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: 0.7405. Min Range: -0.7405

Max Act: 0.7405. Min Act: -0.0000

Data Index: 1861034 (The Pile)

Max Activating Token Index: 826

Text #1

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.3819. Min Act: -0.0000

Data Index: 474037 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.4608. Min Act: -0.0000

Data Index: 441032 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1359977 (The Pile)

Max Activating Token Index: 271

Text #4

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.2347. Min Act: -0.0000

Data Index: 157247 (The Pile)

Max Activating Token Index: 1001

Text #5

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1871602 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.2544. Min Act: -0.0000

Data Index: 413777 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.2134. Min Act: -0.0000

Data Index: 877294 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1945416 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.1999. Min Act: -0.0000

Data Index: 447166 (The Pile)

Max Activating Token Index: 461

Text #10

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.1864. Min Act: -0.0000

Data Index: 471788 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.1858. Min Act: -0.0000

Data Index: 403075 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.2132. Min Act: -0.0000

Data Index: 468118 (The Pile)

Max Activating Token Index: 951

Text #13

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.1956. Min Act: -0.0000

Data Index: 1872914 (The Pile)

Max Activating Token Index: 187

Text #14

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1887850 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.2543. Min Act: -0.0000

Data Index: 247223 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.1715. Min Act: -0.0000

Data Index: 723168 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.1586. Min Act: -0.0000

Data Index: 896975 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1782542 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1892249 (The Pile)

Max Activating Token Index: 409