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

Dataset: The Pile

Neuron 577 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: 1.0085. Min Range: -1.0085

Max Act: 0.9989. Min Act: -0.0000

Data Index: 1446065 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 1.0085. Min Range: -1.0085

Max Act: 1.0085. Min Act: -0.0000

Data Index: 967860 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8687. Min Act: -0.0000

Data Index: 487664 (The Pile)

Max Activating Token Index: 763

Text #3

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1755992 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.9020. Min Act: -0.0000

Data Index: 746232 (The Pile)

Max Activating Token Index: 1000

Text #5

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1882363 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1154656 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1956272 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1042025 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1354199 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.6710. Min Act: -0.0000

Data Index: 932695 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1825886 (The Pile)

Max Activating Token Index: 470

Text #12

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1516777 (The Pile)

Max Activating Token Index: 270

Text #13

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.6024. Min Act: -0.0000

Data Index: 886513 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.6399. Min Act: -0.0000

Data Index: 1397391 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.6088. Min Act: -0.0000

Data Index: 734545 (The Pile)

Max Activating Token Index: 507

Text #16

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1993440 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.6219. Min Act: -0.0000

Data Index: 872950 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.5827. Min Act: -0.0000

Data Index: 367465 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.6977. Min Act: -0.0000

Data Index: 896270 (The Pile)

Max Activating Token Index: 867