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

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

Neuron 1560 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0002

Data Index: 443811 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1322327 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1218832 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0557. Min Act: -0.0002

Data Index: 91549 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0528. Min Act: -0.0002

Data Index: 125924 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1350196 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1310944 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1102114 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0474. Min Act: -0.0002

Data Index: 850062 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1346160 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0501. Min Act: -0.0002

Data Index: 964900 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1158873 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0563. Min Act: -0.0002

Data Index: 374098 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0459. Min Act: -0.0002

Data Index: 79342 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1054879 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0447. Min Act: -0.0002

Data Index: 293431 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0428. Min Act: -0.0002

Data Index: 925000 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1239963 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0543. Min Act: -0.0002

Data Index: 266444 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0452. Min Act: -0.0002

Data Index: 52919 (C4 (Web Text))

Max Activating Token Index: 120