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

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

Neuron 4234 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: 3.4912. Min Range: -3.4912

Max Act: 3.4912. Min Act: -0.0000

Data Index: 14451 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 3.4912. Min Range: -3.4912

Max Act: 2.1490. Min Act: -0.0000

Data Index: 728267 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 3.4912. Min Range: -3.4912

Max Act: 2.1963. Min Act: -0.0000

Data Index: 466317 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.9490. Min Act: -0.0000

Data Index: 547145 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.9780. Min Act: -0.0000

Data Index: 244985 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.8595. Min Act: -0.0000

Data Index: 498685 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.8531. Min Act: -0.0000

Data Index: 843430 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.8713. Min Act: -0.0000

Data Index: 353594 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.8806. Min Act: -0.0000

Data Index: 304930 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.7828. Min Act: -0.0000

Data Index: 208309 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.7330. Min Act: -0.0000

Data Index: 411879 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.7112. Min Act: -0.0000

Data Index: 1338235 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.5595. Min Act: -0.0000

Data Index: 340253 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.6333. Min Act: -0.0000

Data Index: 470656 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.5790. Min Act: -0.0000

Data Index: 1089325 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.7595. Min Act: -0.0000

Data Index: 89079 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.6419. Min Act: -0.0000

Data Index: 115007 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.6707. Min Act: -0.0000

Data Index: 813730 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.6535. Min Act: -0.0000

Data Index: 799881 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 3.4912. Min Range: -3.4912

Max Act: 1.5042. Min Act: -0.0000

Data Index: 1286487 (C4 (Web Text))

Max Activating Token Index: 862