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

Dataset: The Pile

Neuron 4315 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1077855 (The Pile)

Max Activating Token Index: 854

Text #1

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.0533. Min Act: -0.0000

Data Index: 1487766 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9979. Min Act: -0.0000

Data Index: 348628 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1744265 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1009088 (The Pile)

Max Activating Token Index: 295

Text #5

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1131925 (The Pile)

Max Activating Token Index: 810

Text #6

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8155. Min Act: -0.0000

Data Index: 640935 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1335256 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8558. Min Act: -0.0000

Data Index: 999827 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1683492 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8177. Min Act: -0.0000

Data Index: 76184 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8179. Min Act: 0.0000

Data Index: 1515085 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1191003 (The Pile)

Max Activating Token Index: 125

Text #13

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1171158 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7607. Min Act: 0.0000

Data Index: 952549 (The Pile)

Max Activating Token Index: 603

Text #15

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1143994 (The Pile)

Max Activating Token Index: 978

Text #16

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7673. Min Act: -0.0000

Data Index: 52255 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8332. Min Act: -0.0000

Data Index: 164118 (The Pile)

Max Activating Token Index: 998

Text #18

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1443218 (The Pile)

Max Activating Token Index: 516

Text #19

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7757. Min Act: -0.0000

Data Index: 753864 (The Pile)

Max Activating Token Index: 739