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

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

Neuron 462 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: 3.5735. Min Range: -3.5735

Max Act: 3.5735. Min Act: -0.0000

Data Index: 187051 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.1080. Min Act: -0.0000

Data Index: 245912 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.1694. Min Act: -0.0000

Data Index: 27843 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.7693. Min Act: -0.0000

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.6387. Min Act: -0.0000

Data Index: 315360 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.5642. Min Act: -0.0000

Data Index: 1288600 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.2452. Min Act: -0.0000

Data Index: 745364 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.4842. Min Act: -0.0000

Data Index: 1213078 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.1660. Min Act: -0.0000

Data Index: 320477 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.2666. Min Act: -0.0000

Data Index: 109421 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 3.5735. Min Range: -3.5735

Max Act: 1.9646. Min Act: -0.0000

Data Index: 96204 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.2977. Min Act: -0.0000

Data Index: 735024 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.2967. Min Act: -0.0000

Data Index: 161015 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.1128. Min Act: -0.0000

Data Index: 119299 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.1084. Min Act: -0.0000

Data Index: 1004948 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.0858. Min Act: -0.0000

Data Index: 171107 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.0544. Min Act: -0.0000

Data Index: 1009145 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 3.5735. Min Range: -3.5735

Max Act: 2.1145. Min Act: -0.0000

Data Index: 30821 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 3.5735. Min Range: -3.5735

Max Act: 1.8975. Min Act: -0.0000

Data Index: 64873 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 3.5735. Min Range: -3.5735

Max Act: 1.7862. Min Act: -0.0000

Data Index: 272053 (C4 (Web Text))

Max Activating Token Index: 982