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

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

Neuron 610 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.8924. Min Act: -0.0000

Data Index: 132922 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.5636. Min Act: -0.0000

Data Index: 797096 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.5827. Min Act: -0.0000

Data Index: 180885 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3932. Min Act: -0.0000

Data Index: 997588 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.4438. Min Act: -0.0000

Data Index: 923082 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.4294. Min Act: -0.0000

Data Index: 434290 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3549. Min Act: -0.0000

Data Index: 655044 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3816. Min Act: -0.0000

Data Index: 461887 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3862. Min Act: -0.0000

Data Index: 588272 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1337634 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3506. Min Act: -0.0000

Data Index: 503180 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3386. Min Act: -0.0000

Data Index: 964737 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3015. Min Act: -0.0000

Data Index: 766672 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3402. Min Act: -0.0000

Data Index: 256238 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.4081. Min Act: -0.0000

Data Index: 1033667 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.1852. Min Act: -0.0000

Data Index: 29113 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3014. Min Act: -0.0000

Data Index: 1105227 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.2196. Min Act: -0.0000

Data Index: 429002 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1327215 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.2758. Min Act: -0.0000

Data Index: 1197138 (C4 (Web Text))

Max Activating Token Index: 542