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

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

Neuron 3052 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.5632. Min Act: -0.0001

Data Index: 175551 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.5445. Min Act: -0.0001

Data Index: 277020 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.1642. Min Act: -0.0001

Data Index: 360813 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.2213. Min Act: -0.0001

Data Index: 953164 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.2097. Min Act: -0.0001

Data Index: 514618 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.0710. Min Act: -0.0001

Data Index: 756147 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.1321. Min Act: -0.0001

Data Index: 1059653 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.0563. Min Act: -0.0001

Data Index: 136413 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.1516. Min Act: -0.0001

Data Index: 1165897 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.0603. Min Act: -0.0001

Data Index: 184673 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.0464. Min Act: -0.0001

Data Index: 1144746 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.0376. Min Act: -0.0001

Data Index: 497601 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.0410. Min Act: -0.0001

Data Index: 362126 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.0373. Min Act: -0.0001

Data Index: 774977 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.0183. Min Act: -0.0001

Data Index: 848910 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.5632. Min Range: -1.5632

Max Act: 0.9908. Min Act: -0.0001

Data Index: 1092471 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 1.5632. Min Range: -1.5632

Max Act: 0.9605. Min Act: -0.0001

Data Index: 463702 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.0117. Min Act: -0.0001

Data Index: 347030 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 1.5632. Min Range: -1.5632

Max Act: 0.9650. Min Act: -0.0001

Data Index: 1043319 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 1.5632. Min Range: -1.5632

Max Act: 1.0567. Min Act: -0.0001

Data Index: 352967 (C4 (Web Text))

Max Activating Token Index: 562