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

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

Neuron 2270 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.8998. Min Range: -9.8998

Max Act: 9.8998. Min Act: -0.0001

Data Index: 1278643 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 9.8998. Min Range: -9.8998

Max Act: 8.5653. Min Act: -0.0001

Data Index: 730572 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 9.8998. Min Range: -9.8998

Max Act: 8.3528. Min Act: -0.0000

Data Index: 400207 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 9.8998. Min Range: -9.8998

Max Act: 7.4663. Min Act: -0.0001

Data Index: 859303 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 9.8998. Min Range: -9.8998

Max Act: 8.1238. Min Act: -0.0001

Data Index: 1085850 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 9.8998. Min Range: -9.8998

Max Act: 7.9602. Min Act: -0.0000

Data Index: 941160 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 9.8998. Min Range: -9.8998

Max Act: 7.7220. Min Act: -0.0001

Data Index: 497918 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 9.8998. Min Range: -9.8998

Max Act: 7.8321. Min Act: -0.0001

Data Index: 203162 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 9.8998. Min Range: -9.8998

Max Act: 8.1437. Min Act: -0.0000

Data Index: 560508 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 9.8998. Min Range: -9.8998

Max Act: 7.9373. Min Act: -0.0001

Data Index: 325613 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 9.8998. Min Range: -9.8998

Max Act: 7.9071. Min Act: -0.0001

Data Index: 874700 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 9.8998. Min Range: -9.8998

Max Act: 8.0451. Min Act: -0.0000

Data Index: 566857 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 9.8998. Min Range: -9.8998

Max Act: 7.6447. Min Act: -0.0000

Data Index: 128620 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 9.8998. Min Range: -9.8998

Max Act: 7.3696. Min Act: -0.0000

Data Index: 1208098 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 9.8998. Min Range: -9.8998

Max Act: 7.3297. Min Act: -0.0001

Data Index: 444460 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 9.8998. Min Range: -9.8998

Max Act: 7.4371. Min Act: -0.0001

Data Index: 1294434 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 9.8998. Min Range: -9.8998

Max Act: 7.1100. Min Act: -0.0000

Data Index: 222898 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 9.8998. Min Range: -9.8998

Max Act: 7.2537. Min Act: -0.0000

Data Index: 1096073 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 9.8998. Min Range: -9.8998

Max Act: 6.8984. Min Act: -0.0001

Data Index: 1096078 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 9.8998. Min Range: -9.8998

Max Act: 6.9944. Min Act: -0.0001

Data Index: 64161 (C4 (Web Text))

Max Activating Token Index: 357