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

Dataset: The Pile

Neuron 920 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1823414 (The Pile)

Max Activating Token Index: 55

Text #1

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5297. Min Act: -0.0000

Data Index: 151038 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5528. Min Act: -0.0000

Data Index: 175486 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1866956 (The Pile)

Max Activating Token Index: 561

Text #4

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4923. Min Act: -0.0000

Data Index: 894920 (The Pile)

Max Activating Token Index: 389

Text #5

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4789. Min Act: -0.0000

Data Index: 668957 (The Pile)

Max Activating Token Index: 279

Text #6

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4134. Min Act: -0.0000

Data Index: 531206 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1699333 (The Pile)

Max Activating Token Index: 623

Text #8

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4664. Min Act: -0.0000

Data Index: 596445 (The Pile)

Max Activating Token Index: 605

Text #9

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1496695 (The Pile)

Max Activating Token Index: 239

Text #10

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4347. Min Act: -0.0000

Data Index: 281682 (The Pile)

Max Activating Token Index: 16

Text #11

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.3924. Min Act: -0.0000

Data Index: 635073 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1620848 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4206. Min Act: -0.0000

Data Index: 860572 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1377213 (The Pile)

Max Activating Token Index: 47

Text #15

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1769558 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4148. Min Act: -0.0000

Data Index: 656570 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1095182 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4032. Min Act: -0.0000

Data Index: 9333 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.3796. Min Act: -0.0000

Data Index: 942106 (The Pile)

Max Activating Token Index: 831