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

Dataset: The Pile

Neuron 436 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: 2.1949. Min Range: -2.1949

Max Act: 2.1949. Min Act: -0.0000

Data Index: 1701162 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.8862. Min Act: -0.0000

Data Index: 806318 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.4165. Min Act: -0.0000

Data Index: 626152 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.7344. Min Act: -0.0000

Data Index: 1648554 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.5619. Min Act: -0.0000

Data Index: 1203812 (The Pile)

Max Activating Token Index: 828

Text #5

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.5093. Min Act: -0.0000

Data Index: 1799853 (The Pile)

Max Activating Token Index: 955

Text #6

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.4530. Min Act: -0.0000

Data Index: 282294 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.3285. Min Act: -0.0000

Data Index: 1146174 (The Pile)

Max Activating Token Index: 580

Text #8

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1310351 (The Pile)

Max Activating Token Index: 485

Text #9

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.5375. Min Act: -0.0000

Data Index: 480397 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.3531. Min Act: -0.0000

Data Index: 991136 (The Pile)

Max Activating Token Index: 916

Text #11

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.5301. Min Act: -0.0000

Data Index: 881985 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.4341. Min Act: -0.0000

Data Index: 1324549 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.3873. Min Act: -0.0000

Data Index: 97821 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.3877. Min Act: -0.0000

Data Index: 64629 (The Pile)

Max Activating Token Index: 559

Text #15

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.2652. Min Act: -0.0000

Data Index: 624961 (The Pile)

Max Activating Token Index: 870

Text #16

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.1615. Min Act: -0.0000

Data Index: 1452387 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.4240. Min Act: -0.0000

Data Index: 896697 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.2187. Min Act: -0.0000

Data Index: 519317 (The Pile)

Max Activating Token Index: 988

Text #19

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.2311. Min Act: -0.0000

Data Index: 1927926 (The Pile)

Max Activating Token Index: 115