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

Dataset: The Pile

Neuron 1756 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.8993. Min Act: -0.0000

Data Index: 1978526 (The Pile)

Max Activating Token Index: 914

Text #1

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.6744. Min Act: -0.0000

Data Index: 1224281 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.5252. Min Act: -0.0000

Data Index: 1117470 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.6970. Min Act: -0.0000

Data Index: 697172 (The Pile)

Max Activating Token Index: 698

Text #4

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.5453. Min Act: -0.0000

Data Index: 1511342 (The Pile)

Max Activating Token Index: 432

Text #5

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.5161. Min Act: -0.0000

Data Index: 195316 (The Pile)

Max Activating Token Index: 281

Text #6

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.5801. Min Act: -0.0000

Data Index: 1772425 (The Pile)

Max Activating Token Index: 620

Text #7

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.4592. Min Act: -0.0000

Data Index: 726841 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3428. Min Act: -0.0000

Data Index: 1349179 (The Pile)

Max Activating Token Index: 813

Text #9

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.4802. Min Act: -0.0000

Data Index: 1589073 (The Pile)

Max Activating Token Index: 524

Text #10

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.1674. Min Act: -0.0001

Data Index: 223237 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3406. Min Act: -0.0000

Data Index: 1525416 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.4181. Min Act: -0.0001

Data Index: 964605 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1674985 (The Pile)

Max Activating Token Index: 773

Text #14

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.4013. Min Act: -0.0000

Data Index: 1079211 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.2319. Min Act: -0.0000

Data Index: 369961 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.1958. Min Act: -0.0000

Data Index: 687342 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3302. Min Act: -0.0000

Data Index: 776931 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3929. Min Act: -0.0000

Data Index: 1488083 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3939. Min Act: -0.0000

Data Index: 1937189 (The Pile)

Max Activating Token Index: 741