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

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

Neuron 3549 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: 0.9896. Min Range: -0.9896

Max Act: 0.9583. Min Act: -0.0000

Data Index: 997934 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1078726 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9499. Min Act: -0.0000

Data Index: 1140331 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9896. Min Act: -0.0000

Data Index: 141569 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9442. Min Act: -0.0000

Data Index: 620 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9163. Min Act: -0.0000

Data Index: 571453 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1298272 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8882. Min Act: -0.0000

Data Index: 13996 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9419. Min Act: -0.0000

Data Index: 769622 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1217775 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8966. Min Act: -0.0000

Data Index: 441038 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1121434 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8833. Min Act: -0.0000

Data Index: 16536 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8434. Min Act: -0.0000

Data Index: 254363 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8877. Min Act: -0.0000

Data Index: 275486 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8832. Min Act: -0.0000

Data Index: 910575 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8557. Min Act: -0.0000

Data Index: 883972 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8370. Min Act: -0.0000

Data Index: 328294 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8117. Min Act: -0.0000

Data Index: 929767 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7937. Min Act: -0.0000

Data Index: 750389 (C4 (Web Text))

Max Activating Token Index: 1021