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

Dataset: The Pile

Neuron 2550 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: 1.3261. Min Range: -1.3261

Max Act: 1.3261. Min Act: -0.0000

Data Index: 1470842 (The Pile)

Max Activating Token Index: 392

Text #1

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.1496. Min Act: -0.0000

Data Index: 1808343 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1817083 (The Pile)

Max Activating Token Index: 938

Text #3

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.1637. Min Act: -0.0000

Data Index: 1834518 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1556837 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0585. Min Act: -0.0000

Data Index: 354467 (The Pile)

Max Activating Token Index: 420

Text #6

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.1183. Min Act: -0.0000

Data Index: 1084065 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.1064. Min Act: -0.0000

Data Index: 815714 (The Pile)

Max Activating Token Index: 758

Text #8

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.1605. Min Act: -0.0000

Data Index: 49281 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1318846 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0718. Min Act: -0.0000

Data Index: 1541927 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1072076 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0601. Min Act: 0.0000

Data Index: 1060790 (The Pile)

Max Activating Token Index: 264

Text #13

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0443. Min Act: -0.0000

Data Index: 1987205 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0394. Min Act: -0.0000

Data Index: 1549396 (The Pile)

Max Activating Token Index: 739

Text #15

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1583874 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0760. Min Act: -0.0000

Data Index: 221509 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1549241 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 1.3261. Min Range: -1.3261

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1879295 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 1.3261. Min Range: -1.3261

Max Act: 0.9652. Min Act: -0.0000

Data Index: 233724 (The Pile)

Max Activating Token Index: 333