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

Dataset: The Pile

Neuron 282 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8092. Min Range: -5.8092

Max Act: 5.8092. Min Act: -0.0000

Data Index: 1747318 (The Pile)

Max Activating Token Index: 512

Text #1

Max Range: 5.8092. Min Range: -5.8092

Max Act: 4.2461. Min Act: -0.0000

Data Index: 552530 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 5.8092. Min Range: -5.8092

Max Act: 5.1884. Min Act: -0.0000

Data Index: 1186302 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 5.8092. Min Range: -5.8092

Max Act: 3.9247. Min Act: -0.0000

Data Index: 294358 (The Pile)

Max Activating Token Index: 56

Text #4

Max Range: 5.8092. Min Range: -5.8092

Max Act: 4.6504. Min Act: -0.0000

Data Index: 158215 (The Pile)

Max Activating Token Index: 544

Text #5

Max Range: 5.8092. Min Range: -5.8092

Max Act: 4.0613. Min Act: -0.0000

Data Index: 1239564 (The Pile)

Max Activating Token Index: 763

Text #6

Max Range: 5.8092. Min Range: -5.8092

Max Act: 4.2237. Min Act: -0.0000

Data Index: 1290518 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 5.8092. Min Range: -5.8092

Max Act: 3.8345. Min Act: -0.0000

Data Index: 760451 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 5.8092. Min Range: -5.8092

Max Act: 3.6651. Min Act: -0.0000

Data Index: 1316305 (The Pile)

Max Activating Token Index: 281

Text #9

Max Range: 5.8092. Min Range: -5.8092

Max Act: 3.5091. Min Act: -0.0000

Data Index: 627793 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 5.8092. Min Range: -5.8092

Max Act: 3.5902. Min Act: -0.0000

Data Index: 1185865 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 5.8092. Min Range: -5.8092

Max Act: 3.4080. Min Act: -0.0000

Data Index: 1600619 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 5.8092. Min Range: -5.8092

Max Act: 3.0088. Min Act: -0.0000

Data Index: 1703156 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 5.8092. Min Range: -5.8092

Max Act: 3.4800. Min Act: -0.0000

Data Index: 1274682 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 5.8092. Min Range: -5.8092

Max Act: 3.5437. Min Act: -0.0000

Data Index: 1865967 (The Pile)

Max Activating Token Index: 639

Text #15

Max Range: 5.8092. Min Range: -5.8092

Max Act: 3.4244. Min Act: -0.0000

Data Index: 1001538 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 5.8092. Min Range: -5.8092

Max Act: 3.0994. Min Act: -0.0000

Data Index: 1447156 (The Pile)

Max Activating Token Index: 471

Text #17

Max Range: 5.8092. Min Range: -5.8092

Max Act: 2.9401. Min Act: -0.0000

Data Index: 1511618 (The Pile)

Max Activating Token Index: 437

Text #18

Max Range: 5.8092. Min Range: -5.8092

Max Act: 2.7892. Min Act: -0.0000

Data Index: 1128838 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 5.8092. Min Range: -5.8092

Max Act: 3.4113. Min Act: -0.0000

Data Index: 1449752 (The Pile)

Max Activating Token Index: 706