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

Dataset: The Pile

Neuron 2334 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6713. Min Act: -0.0000

Data Index: 1157914 (The Pile)

Max Activating Token Index: 706

Text #1

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.5716. Min Act: -0.0000

Data Index: 797708 (The Pile)

Max Activating Token Index: 789

Text #2

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.6174. Min Act: -0.0000

Data Index: 1361124 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.5255. Min Act: -0.0000

Data Index: 1990991 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.1930. Min Act: -0.0000

Data Index: 1617157 (The Pile)

Max Activating Token Index: 736

Text #5

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.1353. Min Act: -0.0000

Data Index: 1393264 (The Pile)

Max Activating Token Index: 495

Text #6

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.2759. Min Act: -0.0000

Data Index: 267535 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.3941. Min Act: -0.0000

Data Index: 625503 (The Pile)

Max Activating Token Index: 608

Text #8

Max Range: 3.6713. Min Range: -3.6713

Max Act: 2.9914. Min Act: -0.0000

Data Index: 386527 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.1172. Min Act: -0.0000

Data Index: 1365261 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 3.6713. Min Range: -3.6713

Max Act: 2.9897. Min Act: -0.0000

Data Index: 1062799 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.0946. Min Act: -0.0000

Data Index: 405392 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 3.6713. Min Range: -3.6713

Max Act: 2.7815. Min Act: -0.0000

Data Index: 308354 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.0408. Min Act: -0.0000

Data Index: 1169207 (The Pile)

Max Activating Token Index: 466

Text #14

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.0926. Min Act: -0.0000

Data Index: 800429 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 3.6713. Min Range: -3.6713

Max Act: 2.9663. Min Act: -0.0000

Data Index: 167592 (The Pile)

Max Activating Token Index: 909

Text #16

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.0403. Min Act: -0.0000

Data Index: 1430662 (The Pile)

Max Activating Token Index: 703

Text #17

Max Range: 3.6713. Min Range: -3.6713

Max Act: 2.8736. Min Act: -0.0000

Data Index: 308414 (The Pile)

Max Activating Token Index: 1015

Text #18

Max Range: 3.6713. Min Range: -3.6713

Max Act: 3.1038. Min Act: -0.0000

Data Index: 462451 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 3.6713. Min Range: -3.6713

Max Act: 2.9802. Min Act: -0.0000

Data Index: 1123841 (The Pile)

Max Activating Token Index: 773