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

Dataset: The Pile

Neuron 3114 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: 0.6951. Min Range: -0.6951

Max Act: 0.6951. Min Act: -0.0000

Data Index: 162526 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3995. Min Act: -0.0000

Data Index: 777218 (The Pile)

Max Activating Token Index: 366

Text #2

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3804. Min Act: -0.0000

Data Index: 116328 (The Pile)

Max Activating Token Index: 608

Text #3

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1835930 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3361. Min Act: -0.0000

Data Index: 135454 (The Pile)

Max Activating Token Index: 280

Text #5

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1414542 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1321895 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.2703. Min Act: -0.0000

Data Index: 621979 (The Pile)

Max Activating Token Index: 21

Text #8

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1233910 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1685431 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1588549 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3356. Min Act: -0.0000

Data Index: 423527 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.2219. Min Act: -0.0000

Data Index: 211807 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1816772 (The Pile)

Max Activating Token Index: 786

Text #14

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.2331. Min Act: -0.0000

Data Index: 829198 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1773497 (The Pile)

Max Activating Token Index: 638

Text #16

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.2215. Min Act: -0.0000

Data Index: 303834 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.2113. Min Act: -0.0000

Data Index: 274350 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1892468 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.2131. Min Act: -0.0000

Data Index: 642582 (The Pile)

Max Activating Token Index: 98