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

Dataset: The Pile

Neuron 4967 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.1043. Min Act: -0.0000

Data Index: 1534776 (The Pile)

Max Activating Token Index: 6

Text #1

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1421220 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9850. Min Act: -0.0000

Data Index: 434586 (The Pile)

Max Activating Token Index: 875

Text #3

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0528. Min Act: -0.0000

Data Index: 581508 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1203655 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9527. Min Act: -0.0000

Data Index: 376713 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1952145 (The Pile)

Max Activating Token Index: 835

Text #7

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9806. Min Act: -0.0000

Data Index: 1496824 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9672. Min Act: -0.0000

Data Index: 506956 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1130930 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1497188 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1067359 (The Pile)

Max Activating Token Index: 80

Text #12

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1936701 (The Pile)

Max Activating Token Index: 554

Text #13

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8630. Min Act: -0.0000

Data Index: 669377 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8454. Min Act: -0.0000

Data Index: 26790 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1979050 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1652010 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8207. Min Act: -0.0000

Data Index: 988102 (The Pile)

Max Activating Token Index: 235

Text #18

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8719. Min Act: -0.0000

Data Index: 24074 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1722457 (The Pile)

Max Activating Token Index: 869