Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3200 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.8563. Min Act: -0.0001

Data Index: 510732 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.8326. Min Act: -0.0000

Data Index: 125702 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.8494. Min Act: -0.0000

Data Index: 268272 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1102927 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7566. Min Act: -0.0000

Data Index: 870252 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1059060 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6826. Min Act: -0.0000

Data Index: 122985 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1202938 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6954. Min Act: -0.0000

Data Index: 668290 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1100831 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7248. Min Act: -0.0000

Data Index: 809737 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1236410 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6932. Min Act: -0.0000

Data Index: 735215 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6865. Min Act: -0.0000

Data Index: 649357 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6581. Min Act: -0.0000

Data Index: 610061 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1160040 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6613. Min Act: -0.0000

Data Index: 112984 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1131426 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6947. Min Act: -0.0000

Data Index: 815428 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6622. Min Act: -0.0000

Data Index: 41687 (C4 (Web Text))

Max Activating Token Index: 943