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

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

Neuron 2632 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0607. Min Range: -4.0607

Max Act: 4.0607. Min Act: -0.0000

Data Index: 837276 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 4.0607. Min Range: -4.0607

Max Act: 3.8505. Min Act: -0.0000

Data Index: 716891 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 4.0607. Min Range: -4.0607

Max Act: 3.5494. Min Act: -0.0000

Data Index: 1208462 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 4.0607. Min Range: -4.0607

Max Act: 3.6276. Min Act: -0.0000

Data Index: 313826 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 4.0607. Min Range: -4.0607

Max Act: 3.0105. Min Act: -0.0000

Data Index: 1164978 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.9191. Min Act: -0.0000

Data Index: 825568 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.9021. Min Act: -0.0000

Data Index: 114326 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.7098. Min Act: -0.0000

Data Index: 835980 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.8162. Min Act: -0.0000

Data Index: 779123 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.8064. Min Act: -0.0000

Data Index: 236154 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.7880. Min Act: -0.0000

Data Index: 1316162 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.7509. Min Act: -0.0000

Data Index: 1349263 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.7026. Min Act: -0.0000

Data Index: 509827 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.7862. Min Act: -0.0000

Data Index: 1228553 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.4804. Min Act: -0.0000

Data Index: 486947 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.5774. Min Act: -0.0000

Data Index: 179902 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.7266. Min Act: -0.0000

Data Index: 242916 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.5425. Min Act: -0.0000

Data Index: 1020802 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.6673. Min Act: -0.0000

Data Index: 1066039 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 4.0607. Min Range: -4.0607

Max Act: 2.3976. Min Act: -0.0000

Data Index: 721977 (C4 (Web Text))

Max Activating Token Index: 572