Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2837 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0811. Min Range: -1.0811

Max Act: 1.0585. Min Act: -0.0000

Data Index: 164320 (The Pile)

Max Activating Token Index: 225

Text #1

Max Range: 1.0811. Min Range: -1.0811

Max Act: 1.0032. Min Act: -0.0001

Data Index: 1746634 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 1.0811. Min Range: -1.0811

Max Act: 1.0676. Min Act: -0.0000

Data Index: 1367262 (The Pile)

Max Activating Token Index: 1017

Text #3

Max Range: 1.0811. Min Range: -1.0811

Max Act: 1.0575. Min Act: -0.0000

Data Index: 895966 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 1.0811. Min Range: -1.0811

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1772117 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.9157. Min Act: -0.0000

Data Index: 318746 (The Pile)

Max Activating Token Index: 328

Text #6

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1178785 (The Pile)

Max Activating Token Index: 25

Text #7

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.9093. Min Act: -0.0000

Data Index: 915715 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1782403 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.8929. Min Act: -0.0000

Data Index: 1700942 (The Pile)

Max Activating Token Index: 388

Text #10

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.8364. Min Act: -0.0000

Data Index: 280610 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.9143. Min Act: -0.0000

Data Index: 471894 (The Pile)

Max Activating Token Index: 9

Text #12

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1592279 (The Pile)

Max Activating Token Index: 257

Text #13

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.9120. Min Act: -0.0000

Data Index: 995725 (The Pile)

Max Activating Token Index: 134

Text #14

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.8847. Min Act: -0.0000

Data Index: 243663 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.8084. Min Act: -0.0000

Data Index: 139159 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.8264. Min Act: -0.0000

Data Index: 235942 (The Pile)

Max Activating Token Index: 927

Text #17

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.8501. Min Act: -0.0000

Data Index: 451336 (The Pile)

Max Activating Token Index: 292

Text #18

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1693808 (The Pile)

Max Activating Token Index: 231

Text #19

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1329932 (The Pile)

Max Activating Token Index: 365