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

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

Neuron 1807 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.7104. Min Act: -0.0000

Data Index: 1071382 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1154244 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6510. Min Act: -0.0000

Data Index: 259627 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6785. Min Act: -0.0000

Data Index: 663513 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1303596 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6289. Min Act: -0.0000

Data Index: 571889 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6292. Min Act: -0.0000

Data Index: 547036 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1039603 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6050. Min Act: -0.0000

Data Index: 39159 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5750. Min Act: -0.0000

Data Index: 633486 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.6038. Min Act: -0.0000

Data Index: 119276 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5701. Min Act: -0.0000

Data Index: 347987 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5907. Min Act: -0.0000

Data Index: 462180 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5660. Min Act: -0.0000

Data Index: 189987 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1044540 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5297. Min Act: -0.0000

Data Index: 460364 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1369687 (Python Code)

Max Activating Token Index: 667

Text #17

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4918. Min Act: -0.0000

Data Index: 988917 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1287317 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4449. Min Act: -0.0000

Data Index: 888145 (C4 (Web Text))

Max Activating Token Index: 652