Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2777 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5373. Min Act: -0.0000

Data Index: 1441307 (The Pile)

Max Activating Token Index: 514

Text #1

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.6465. Min Act: -0.0000

Data Index: 186361 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.1641. Min Act: -0.0000

Data Index: 539645 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.3771. Min Act: -0.0000

Data Index: 1413442 (The Pile)

Max Activating Token Index: 871

Text #4

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.2231. Min Act: -0.0000

Data Index: 1003088 (The Pile)

Max Activating Token Index: 743

Text #5

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.3018. Min Act: -0.0000

Data Index: 1606276 (The Pile)

Max Activating Token Index: 763

Text #6

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.1570. Min Act: -0.0000

Data Index: 630634 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.2692. Min Act: -0.0000

Data Index: 1640330 (The Pile)

Max Activating Token Index: 75

Text #8

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.1564. Min Act: -0.0000

Data Index: 1817867 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1539861 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.2151. Min Act: -0.0000

Data Index: 20489 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1549936 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.0955. Min Act: -0.0000

Data Index: 152667 (The Pile)

Max Activating Token Index: 871

Text #13

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.0312. Min Act: -0.0000

Data Index: 308215 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.0240. Min Act: -0.0000

Data Index: 1099255 (The Pile)

Max Activating Token Index: 991

Text #15

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.1683. Min Act: -0.0000

Data Index: 1283820 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.0868. Min Act: -0.0000

Data Index: 1943451 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 1.6465. Min Range: -1.6465

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1780074 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.0672. Min Act: -0.0000

Data Index: 1906563 (The Pile)

Max Activating Token Index: 884

Text #19

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.0525. Min Act: -0.0000

Data Index: 339782 (The Pile)

Max Activating Token Index: 718