Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2100 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2211. Min Act: -0.0000

Data Index: 292057 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1651378 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1465607 (The Pile)

Max Activating Token Index: 676

Text #3

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1622437 (The Pile)

Max Activating Token Index: 272

Text #4

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1141318 (The Pile)

Max Activating Token Index: 219

Text #5

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1167759 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1645. Min Act: -0.0000

Data Index: 1956037 (The Pile)

Max Activating Token Index: 891

Text #7

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1797929 (The Pile)

Max Activating Token Index: 972

Text #8

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1540192 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1783411 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1556. Min Act: -0.0000

Data Index: 327040 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1549. Min Act: -0.0000

Data Index: 998250 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1140168 (The Pile)

Max Activating Token Index: 194

Text #13

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1545. Min Act: -0.0000

Data Index: 174920 (The Pile)

Max Activating Token Index: 141

Text #14

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1536. Min Act: -0.0000

Data Index: 887544 (The Pile)

Max Activating Token Index: 316

Text #15

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1206807 (The Pile)

Max Activating Token Index: 756

Text #16

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1499. Min Act: -0.0000

Data Index: 424352 (The Pile)

Max Activating Token Index: 21

Text #17

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1518942 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1071408 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1447. Min Act: -0.0000

Data Index: 285896 (The Pile)

Max Activating Token Index: 449