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

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

Neuron 2793 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.7547. Min Act: -0.0000

Data Index: 938743 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6910. Min Act: -0.0000

Data Index: 666617 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1075489 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6877. Min Act: -0.0000

Data Index: 960025 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6201. Min Act: -0.0000

Data Index: 665768 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.5966. Min Act: -0.0000

Data Index: 892323 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6364. Min Act: -0.0000

Data Index: 156033 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.4680. Min Act: -0.0000

Data Index: 801655 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.4412. Min Act: -0.0000

Data Index: 383108 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1102363 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.4036. Min Act: -0.0000

Data Index: 717879 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1185819 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.4113. Min Act: -0.0000

Data Index: 875902 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.4054. Min Act: -0.0000

Data Index: 840275 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.3885. Min Act: -0.0000

Data Index: 952430 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.3867. Min Act: -0.0000

Data Index: 98948 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.3883. Min Act: -0.0000

Data Index: 955628 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1269406 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.3838. Min Act: -0.0000

Data Index: 330148 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.3922. Min Act: -0.0000

Data Index: 776179 (C4 (Web Text))

Max Activating Token Index: 735