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

Dataset: The Pile

Neuron 2951 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: 0.6922. Min Range: -0.6922

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1223571 (The Pile)

Max Activating Token Index: 501

Text #1

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1310658 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1361124 (The Pile)

Max Activating Token Index: 402

Text #3

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1337219 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1560647 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.6712. Min Act: -0.0000

Data Index: 670176 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1881467 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1331595 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1169973 (The Pile)

Max Activating Token Index: 885

Text #9

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.5649. Min Act: -0.0000

Data Index: 172465 (The Pile)

Max Activating Token Index: 457

Text #10

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.5561. Min Act: -0.0000

Data Index: 367546 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1707223 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.5806. Min Act: -0.0000

Data Index: 331480 (The Pile)

Max Activating Token Index: 857

Text #13

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.5645. Min Act: -0.0000

Data Index: 190442 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.5402. Min Act: 0.0000

Data Index: 1299976 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1187746 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.5230. Min Act: -0.0000

Data Index: 629343 (The Pile)

Max Activating Token Index: 108

Text #17

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.5349. Min Act: -0.0000

Data Index: 684923 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1370882 (The Pile)

Max Activating Token Index: 602

Text #19

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.4865. Min Act: -0.0000

Data Index: 139372 (The Pile)

Max Activating Token Index: 814