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

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

Neuron 3659 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.9433. Min Act: -0.0000

Data Index: 19263 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1160822 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8597. Min Act: -0.0000

Data Index: 408190 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8109. Min Act: -0.0000

Data Index: 995717 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8085. Min Act: -0.0000

Data Index: 278336 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7731. Min Act: -0.0000

Data Index: 701394 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7391. Min Act: -0.0000

Data Index: 611406 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7155. Min Act: -0.0000

Data Index: 22635 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7173. Min Act: -0.0000

Data Index: 702467 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7213. Min Act: -0.0000

Data Index: 974125 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7018. Min Act: -0.0000

Data Index: 978627 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1281002 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1188920 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1328228 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7071. Min Act: -0.0000

Data Index: 710552 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6703. Min Act: -0.0000

Data Index: 192641 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7109. Min Act: -0.0000

Data Index: 716864 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1205573 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6846. Min Act: -0.0000

Data Index: 705811 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6566. Min Act: -0.0000

Data Index: 586819 (C4 (Web Text))

Max Activating Token Index: 444