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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3966 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7607. Min Act: -0.0000

Data Index: 657077 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1234210 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7399. Min Act: 0.0000

Data Index: 1094803 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6946. Min Act: -0.0000

Data Index: 712725 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6694. Min Act: -0.0000

Data Index: 680099 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6851. Min Act: -0.0000

Data Index: 396139 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6529. Min Act: 0.0000

Data Index: 1260243 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1073230 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6320. Min Act: -0.0000

Data Index: 668619 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5943. Min Act: 0.0002

Data Index: 1153452 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6038. Min Act: 0.0000

Data Index: 1049613 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5764. Min Act: -0.0000

Data Index: 164898 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1068717 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1263903 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5969. Min Act: -0.0000

Data Index: 949724 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6108. Min Act: -0.0000

Data Index: 221313 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5731. Min Act: -0.0000

Data Index: 401849 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5549. Min Act: -0.0000

Data Index: 16082 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5847. Min Act: -0.0000

Data Index: 235719 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5367. Min Act: -0.0000

Data Index: 468446 (C4 (Web Text))

Max Activating Token Index: 16