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

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

Neuron 1937 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0123. Min Range: -1.0123

Max Act: 1.0123. Min Act: -0.0001

Data Index: 111725 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.7748. Min Act: -0.0001

Data Index: 1153186 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.8309. Min Act: -0.0001

Data Index: 1168062 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.7543. Min Act: -0.0001

Data Index: 727329 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.7519. Min Act: -0.0001

Data Index: 352069 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.7518. Min Act: -0.0001

Data Index: 480393 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.7497. Min Act: -0.0001

Data Index: 743733 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.7852. Min Act: -0.0001

Data Index: 87445 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.7545. Min Act: -0.0001

Data Index: 896420 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.7078. Min Act: -0.0001

Data Index: 354669 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.7487. Min Act: -0.0001

Data Index: 666969 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.7063. Min Act: -0.0001

Data Index: 52915 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.7025. Min Act: -0.0001

Data Index: 290347 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.6553. Min Act: -0.0001

Data Index: 643232 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.7009. Min Act: -0.0001

Data Index: 125608 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.6631. Min Act: -0.0001

Data Index: 32285 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.6106. Min Act: -0.0001

Data Index: 1218655 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.6309. Min Act: -0.0001

Data Index: 1051572 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.5923. Min Act: -0.0001

Data Index: 431375 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 1.0123. Min Range: -1.0123

Max Act: 0.6526. Min Act: -0.0001

Data Index: 466732 (C4 (Web Text))

Max Activating Token Index: 240