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

Dataset: The Pile

Neuron 2282 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.9236. Min Act: -0.0000

Data Index: 490627 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.4662. Min Act: -0.0000

Data Index: 1800512 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.7263. Min Act: -0.0000

Data Index: 1393201 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.5527. Min Act: 0.0001

Data Index: 134866 (The Pile)

Max Activating Token Index: 774

Text #4

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.3852. Min Act: -0.0000

Data Index: 1111802 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.3729. Min Act: -0.0000

Data Index: 1572002 (The Pile)

Max Activating Token Index: 434

Text #6

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.5137. Min Act: -0.0000

Data Index: 1070047 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.5900. Min Act: -0.0000

Data Index: 1584406 (The Pile)

Max Activating Token Index: 356

Text #8

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.4483. Min Act: -0.0000

Data Index: 868573 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.4118. Min Act: -0.0000

Data Index: 1766729 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.3833. Min Act: -0.0000

Data Index: 369805 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.5341. Min Act: -0.0000

Data Index: 888887 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.3079. Min Act: -0.0000

Data Index: 1909270 (The Pile)

Max Activating Token Index: 850

Text #13

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.2566. Min Act: 0.0001

Data Index: 1257023 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 3.9236. Min Range: -3.9236

Max Act: 2.9932. Min Act: -0.0000

Data Index: 1369860 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.0785. Min Act: -0.0000

Data Index: 1521301 (The Pile)

Max Activating Token Index: 649

Text #16

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.2588. Min Act: -0.0000

Data Index: 1333079 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.2506. Min Act: 0.0000

Data Index: 224232 (The Pile)

Max Activating Token Index: 113

Text #18

Max Range: 3.9236. Min Range: -3.9236

Max Act: 2.7911. Min Act: -0.0000

Data Index: 1256820 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 3.9236. Min Range: -3.9236

Max Act: 3.2364. Min Act: -0.0000

Data Index: 13811 (The Pile)

Max Activating Token Index: 36