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

Dataset: The Pile

Neuron 2546 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: 3.6943. Min Range: -3.6943

Max Act: 3.6943. Min Act: -0.0000

Data Index: 1039676 (The Pile)

Max Activating Token Index: 447

Text #1

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.5067. Min Act: -0.0000

Data Index: 1910416 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.4637. Min Act: -0.0000

Data Index: 688790 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.4750. Min Act: -0.0000

Data Index: 128251 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.2689. Min Act: -0.0000

Data Index: 1921060 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.1116. Min Act: -0.0000

Data Index: 81704 (The Pile)

Max Activating Token Index: 70

Text #6

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.8886. Min Act: -0.0000

Data Index: 1434613 (The Pile)

Max Activating Token Index: 609

Text #7

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.8663. Min Act: -0.0000

Data Index: 1354793 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 3.6943. Min Range: -3.6943

Max Act: 3.0165. Min Act: -0.0000

Data Index: 1545238 (The Pile)

Max Activating Token Index: 792

Text #9

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.9871. Min Act: -0.0000

Data Index: 218236 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.8046. Min Act: -0.0000

Data Index: 1203693 (The Pile)

Max Activating Token Index: 59

Text #11

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.7584. Min Act: -0.0000

Data Index: 1954723 (The Pile)

Max Activating Token Index: 805

Text #12

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.8763. Min Act: -0.0000

Data Index: 574197 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.8730. Min Act: -0.0000

Data Index: 41468 (The Pile)

Max Activating Token Index: 322

Text #14

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.7405. Min Act: -0.0000

Data Index: 1346346 (The Pile)

Max Activating Token Index: 45

Text #15

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.6373. Min Act: -0.0000

Data Index: 214068 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.9258. Min Act: -0.0000

Data Index: 1943993 (The Pile)

Max Activating Token Index: 980

Text #17

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.7548. Min Act: -0.0000

Data Index: 1385353 (The Pile)

Max Activating Token Index: 460

Text #18

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.6015. Min Act: -0.0000

Data Index: 894303 (The Pile)

Max Activating Token Index: 236

Text #19

Max Range: 3.6943. Min Range: -3.6943

Max Act: 2.5828. Min Act: -0.0000

Data Index: 958078 (The Pile)

Max Activating Token Index: 698