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

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

Neuron 5218 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9768. Min Range: -4.9768

Max Act: 4.9768. Min Act: -0.0000

Data Index: 1288799 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.5689. Min Act: -0.0000

Data Index: 416295 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.8162. Min Act: -0.0000

Data Index: 633406 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.4588. Min Act: -0.0000

Data Index: 1145720 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.6057. Min Act: -0.0000

Data Index: 214962 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.1650. Min Act: -0.0000

Data Index: 794852 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.4713. Min Act: -0.0000

Data Index: 1131491 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.3934. Min Act: -0.0000

Data Index: 107616 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.3864. Min Act: -0.0000

Data Index: 1298936 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.3455. Min Act: -0.0000

Data Index: 1239468 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.1435. Min Act: -0.0000

Data Index: 292367 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.3135. Min Act: -0.0000

Data Index: 447948 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.4720. Min Act: -0.0000

Data Index: 300122 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.4669. Min Act: -0.0000

Data Index: 579726 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.4559. Min Act: -0.0000

Data Index: 938106 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 4.9768. Min Range: -4.9768

Max Act: 2.8708. Min Act: -0.0000

Data Index: 1304209 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.1983. Min Act: -0.0000

Data Index: 481104 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.3641. Min Act: -0.0000

Data Index: 678428 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.3659. Min Act: -0.0000

Data Index: 948603 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 4.9768. Min Range: -4.9768

Max Act: 3.2631. Min Act: -0.0000

Data Index: 1210110 (C4 (Web Text))

Max Activating Token Index: 268