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

Dataset: The Pile

Neuron 1445 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: 0.8453. Min Range: -0.8453

Max Act: 0.8453. Min Act: -0.0000

Data Index: 934569 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7800. Min Act: -0.0000

Data Index: 757559 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7456. Min Act: -0.0000

Data Index: 319238 (The Pile)

Max Activating Token Index: 620

Text #3

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7373. Min Act: 0.0000

Data Index: 1255525 (The Pile)

Max Activating Token Index: 639

Text #4

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1313983 (The Pile)

Max Activating Token Index: 830

Text #5

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6536. Min Act: -0.0000

Data Index: 225607 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5613. Min Act: -0.0000

Data Index: 913887 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1502992 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5927. Min Act: -0.0000

Data Index: 910731 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6420. Min Act: -0.0000

Data Index: 170799 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5795. Min Act: -0.0000

Data Index: 840017 (The Pile)

Max Activating Token Index: 977

Text #11

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5734. Min Act: -0.0000

Data Index: 497255 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5715. Min Act: -0.0000

Data Index: 34281 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5689. Min Act: -0.0000

Data Index: 844424 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1594359 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1652698 (The Pile)

Max Activating Token Index: 137

Text #16

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1578409 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5156. Min Act: -0.0000

Data Index: 890757 (The Pile)

Max Activating Token Index: 40

Text #18

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1333119 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1070540 (The Pile)

Max Activating Token Index: 21