Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 227 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.6307. Min Act: -0.0001

Data Index: 1352496 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.6528. Min Act: -0.0001

Data Index: 47773 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.6100. Min Act: -0.0001

Data Index: 81961 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.6281. Min Act: -0.0001

Data Index: 127917 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5766. Min Act: -0.0001

Data Index: 249295 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5722. Min Act: -0.0001

Data Index: 353977 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5708. Min Act: -0.0001

Data Index: 758440 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5192. Min Act: -0.0001

Data Index: 1100568 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5324. Min Act: -0.0001

Data Index: 1267966 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4967. Min Act: -0.0001

Data Index: 1196127 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5388. Min Act: -0.0001

Data Index: 126278 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5322. Min Act: -0.0001

Data Index: 619517 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5459. Min Act: -0.0001

Data Index: 1085058 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5474. Min Act: -0.0001

Data Index: 162499 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4955. Min Act: -0.0001

Data Index: 34412 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5029. Min Act: -0.0001

Data Index: 540180 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5003. Min Act: -0.0001

Data Index: 662041 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4941. Min Act: -0.0001

Data Index: 292023 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5452. Min Act: -0.0001

Data Index: 1189628 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5007. Min Act: -0.0001

Data Index: 274722 (C4 (Web Text))

Max Activating Token Index: 807