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

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

Neuron 3744 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: 1.3445. Min Range: -1.3445

Max Act: 1.3445. Min Act: -0.0000

Data Index: 742411 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.2612. Min Act: -0.0000

Data Index: 400141 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.2645. Min Act: -0.0000

Data Index: 1296878 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.9975. Min Act: -0.0000

Data Index: 607881 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.9436. Min Act: -0.0000

Data Index: 183919 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.9355. Min Act: -0.0000

Data Index: 461889 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.8066. Min Act: -0.0000

Data Index: 609636 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.8083. Min Act: -0.0000

Data Index: 864187 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1038324 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.7827. Min Act: -0.0000

Data Index: 215200 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.6860. Min Act: -0.0000

Data Index: 837371 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.7964. Min Act: -0.0000

Data Index: 714921 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.6991. Min Act: -0.0000

Data Index: 60883 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1322552 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.7371. Min Act: -0.0000

Data Index: 522230 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.7091. Min Act: -0.0000

Data Index: 556827 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.7339. Min Act: -0.0000

Data Index: 10423 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1312263 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1099860 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1067616 (C4 (Web Text))

Max Activating Token Index: 63