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

Dataset: The Pile

Neuron 632 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1396523 (The Pile)

Max Activating Token Index: 376

Text #1

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7741. Min Act: -0.0000

Data Index: 484722 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1390903 (The Pile)

Max Activating Token Index: 318

Text #3

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1534359 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1389457 (The Pile)

Max Activating Token Index: 1010

Text #5

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1860888 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1404031 (The Pile)

Max Activating Token Index: 655

Text #7

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6668. Min Act: -0.0000

Data Index: 252854 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6833. Min Act: -0.0000

Data Index: 850636 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6329. Min Act: -0.0000

Data Index: 405457 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6307. Min Act: -0.0000

Data Index: 512046 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6442. Min Act: -0.0000

Data Index: 449823 (The Pile)

Max Activating Token Index: 250

Text #12

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1142266 (The Pile)

Max Activating Token Index: 389

Text #13

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1574385 (The Pile)

Max Activating Token Index: 513

Text #14

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1166968 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6247. Min Act: -0.0000

Data Index: 759480 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1763576 (The Pile)

Max Activating Token Index: 387

Text #17

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1278594 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5183. Min Act: -0.0000

Data Index: 662479 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6148. Min Act: -0.0000

Data Index: 854312 (The Pile)

Max Activating Token Index: 579