Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 719 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.3716. Min Act: -0.0000

Data Index: 330787 (The Pile)

Max Activating Token Index: 861

Text #1

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.2735. Min Act: -0.0000

Data Index: 186416 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.3043. Min Act: -0.0000

Data Index: 165127 (The Pile)

Max Activating Token Index: 250

Text #3

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.2070. Min Act: -0.0000

Data Index: 500058 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1582. Min Act: -0.0000

Data Index: 1330486 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1644. Min Act: -0.0000

Data Index: 263059 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1362270 (The Pile)

Max Activating Token Index: 44

Text #7

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1772. Min Act: -0.0000

Data Index: 1210479 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1099. Min Act: -0.0000

Data Index: 166367 (The Pile)

Max Activating Token Index: 78

Text #9

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1230041 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0876. Min Act: -0.0000

Data Index: 752059 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1304. Min Act: -0.0000

Data Index: 478291 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1758192 (The Pile)

Max Activating Token Index: 848

Text #13

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0865. Min Act: -0.0000

Data Index: 656393 (The Pile)

Max Activating Token Index: 239

Text #14

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1420769 (The Pile)

Max Activating Token Index: 603

Text #15

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1112292 (The Pile)

Max Activating Token Index: 339

Text #16

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1022155 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.9821. Min Act: -0.0000

Data Index: 1257075 (The Pile)

Max Activating Token Index: 432

Text #18

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0964. Min Act: -0.0000

Data Index: 228937 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1456. Min Act: -0.0000

Data Index: 665852 (The Pile)

Max Activating Token Index: 900