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

Dataset: The Pile

Neuron 1039 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: 5.2334. Min Range: -5.2334

Max Act: 5.2334. Min Act: -0.0000

Data Index: 1446082 (The Pile)

Max Activating Token Index: 975

Text #1

Max Range: 5.2334. Min Range: -5.2334

Max Act: 4.7278. Min Act: -0.0000

Data Index: 1960409 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 5.2334. Min Range: -5.2334

Max Act: 4.7747. Min Act: 0.0000

Data Index: 1247306 (The Pile)

Max Activating Token Index: 800

Text #3

Max Range: 5.2334. Min Range: -5.2334

Max Act: 4.7735. Min Act: -0.0000

Data Index: 1259413 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 5.2334. Min Range: -5.2334

Max Act: 4.4676. Min Act: -0.0000

Data Index: 607875 (The Pile)

Max Activating Token Index: 104

Text #5

Max Range: 5.2334. Min Range: -5.2334

Max Act: 4.4783. Min Act: -0.0000

Data Index: 1359355 (The Pile)

Max Activating Token Index: 561

Text #6

Max Range: 5.2334. Min Range: -5.2334

Max Act: 4.1597. Min Act: -0.0000

Data Index: 634751 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 5.2334. Min Range: -5.2334

Max Act: 4.3666. Min Act: 0.0000

Data Index: 1403890 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 5.2334. Min Range: -5.2334

Max Act: 4.2922. Min Act: -0.0000

Data Index: 727393 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 5.2334. Min Range: -5.2334

Max Act: 4.0931. Min Act: -0.0000

Data Index: 671772 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 5.2334. Min Range: -5.2334

Max Act: 4.2455. Min Act: -0.0000

Data Index: 1034482 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 5.2334. Min Range: -5.2334

Max Act: 4.0040. Min Act: -0.0000

Data Index: 221069 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 5.2334. Min Range: -5.2334

Max Act: 3.9189. Min Act: -0.0000

Data Index: 1123985 (The Pile)

Max Activating Token Index: 245

Text #13

Max Range: 5.2334. Min Range: -5.2334

Max Act: 3.8025. Min Act: -0.0000

Data Index: 1194683 (The Pile)

Max Activating Token Index: 824

Text #14

Max Range: 5.2334. Min Range: -5.2334

Max Act: 4.0946. Min Act: 0.0000

Data Index: 112764 (The Pile)

Max Activating Token Index: 51

Text #15

Max Range: 5.2334. Min Range: -5.2334

Max Act: 3.8898. Min Act: 0.0000

Data Index: 111789 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 5.2334. Min Range: -5.2334

Max Act: 3.7703. Min Act: -0.0000

Data Index: 1754571 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 5.2334. Min Range: -5.2334

Max Act: 3.7607. Min Act: -0.0000

Data Index: 158807 (The Pile)

Max Activating Token Index: 655

Text #18

Max Range: 5.2334. Min Range: -5.2334

Max Act: 3.9287. Min Act: -0.0000

Data Index: 1475566 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 5.2334. Min Range: -5.2334

Max Act: 3.9043. Min Act: -0.0000

Data Index: 1301833 (The Pile)

Max Activating Token Index: 289