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

Dataset: The Pile

Neuron 2986 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: 3.7507. Min Range: -3.7507

Max Act: 3.5414. Min Act: -0.0000

Data Index: 1102772 (The Pile)

Max Activating Token Index: 702

Text #1

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.6299. Min Act: -0.0000

Data Index: 1023314 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.7507. Min Act: -0.0000

Data Index: 1309841 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.5968. Min Act: -0.0000

Data Index: 1897949 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.5671. Min Act: -0.0000

Data Index: 1149436 (The Pile)

Max Activating Token Index: 7

Text #5

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.3753. Min Act: -0.0000

Data Index: 1923621 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.5104. Min Act: -0.0000

Data Index: 1623718 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1425. Min Act: -0.0000

Data Index: 90755 (The Pile)

Max Activating Token Index: 346

Text #8

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.2518. Min Act: -0.0000

Data Index: 1478442 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.2706. Min Act: -0.0000

Data Index: 1034494 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.2214. Min Act: -0.0000

Data Index: 1364090 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1915. Min Act: -0.0000

Data Index: 1963790 (The Pile)

Max Activating Token Index: 95

Text #12

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1796. Min Act: -0.0000

Data Index: 313048 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1403. Min Act: -0.0000

Data Index: 1440341 (The Pile)

Max Activating Token Index: 681

Text #14

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1431. Min Act: -0.0000

Data Index: 207527 (The Pile)

Max Activating Token Index: 489

Text #15

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.0086. Min Act: -0.0000

Data Index: 982009 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1042. Min Act: -0.0000

Data Index: 436122 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.0625. Min Act: -0.0000

Data Index: 869077 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.0466. Min Act: -0.0000

Data Index: 799153 (The Pile)

Max Activating Token Index: 694

Text #19

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.0432. Min Act: -0.0000

Data Index: 567082 (The Pile)

Max Activating Token Index: 539