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

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

Neuron 1304 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6925. Min Act: -0.0000

Data Index: 866951 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6765. Min Act: -0.0000

Data Index: 427399 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6088. Min Act: -0.0000

Data Index: 417472 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6066. Min Act: -0.0000

Data Index: 795787 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.6400. Min Act: -0.0000

Data Index: 655785 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5918. Min Act: -0.0000

Data Index: 760776 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5912. Min Act: -0.0000

Data Index: 575152 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5681. Min Act: -0.0000

Data Index: 196852 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5641. Min Act: -0.0000

Data Index: 999726 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1527822 (Python Code)

Max Activating Token Index: 992

Text #10

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1094185 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5754. Min Act: -0.0000

Data Index: 559662 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5741. Min Act: -0.0000

Data Index: 949206 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5712. Min Act: -0.0000

Data Index: 800918 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5681. Min Act: -0.0000

Data Index: 438615 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1317568 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5588. Min Act: -0.0000

Data Index: 794652 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1469359 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5937. Min Act: -0.0000

Data Index: 673289 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.6925. Min Range: -0.6925

Max Act: 0.5399. Min Act: -0.0000

Data Index: 201413 (C4 (Web Text))

Max Activating Token Index: 509