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

Dataset: The Pile

Neuron 2178 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0019. Min Range: -3.0019

Max Act: 3.0019. Min Act: -0.0000

Data Index: 70171 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.6356. Min Act: 0.0000

Data Index: 170472 (The Pile)

Max Activating Token Index: 266

Text #2

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.5991. Min Act: 0.0000

Data Index: 47819 (The Pile)

Max Activating Token Index: 687

Text #3

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.3984. Min Act: -0.0000

Data Index: 393962 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.0753. Min Act: -0.0000

Data Index: 666881 (The Pile)

Max Activating Token Index: 898

Text #5

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.2492. Min Act: -0.0000

Data Index: 1148681 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.3800. Min Act: -0.0000

Data Index: 1353290 (The Pile)

Max Activating Token Index: 628

Text #7

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.4467. Min Act: -0.0000

Data Index: 726125 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.2528. Min Act: -0.0000

Data Index: 308633 (The Pile)

Max Activating Token Index: 526

Text #9

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.2918. Min Act: -0.0000

Data Index: 1263226 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.3214. Min Act: -0.0000

Data Index: 1116405 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.2043. Min Act: -0.0000

Data Index: 1326263 (The Pile)

Max Activating Token Index: 650

Text #12

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.2070. Min Act: -0.0000

Data Index: 1458571 (The Pile)

Max Activating Token Index: 991

Text #13

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.1943. Min Act: -0.0000

Data Index: 518309 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.1682. Min Act: -0.0000

Data Index: 934566 (The Pile)

Max Activating Token Index: 795

Text #15

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.1447. Min Act: 0.0000

Data Index: 514808 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 3.0019. Min Range: -3.0019

Max Act: 1.9137. Min Act: -0.0000

Data Index: 1068903 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.0886. Min Act: -0.0000

Data Index: 365622 (The Pile)

Max Activating Token Index: 906

Text #18

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.0704. Min Act: -0.0000

Data Index: 18047 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 3.0019. Min Range: -3.0019

Max Act: 1.9717. Min Act: -0.0000

Data Index: 303670 (The Pile)

Max Activating Token Index: 357