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

Dataset: The Pile

Neuron 718 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: 0.9330. Min Range: -0.9330

Max Act: 0.9330. Min Act: -0.0000

Data Index: 286836 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.8826. Min Act: -0.0000

Data Index: 656393 (The Pile)

Max Activating Token Index: 291

Text #2

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1615101 (The Pile)

Max Activating Token Index: 429

Text #3

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7943. Min Act: -0.0000

Data Index: 1182077 (The Pile)

Max Activating Token Index: 126

Text #4

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1417136 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1288768 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1171934 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6619. Min Act: -0.0000

Data Index: 235239 (The Pile)

Max Activating Token Index: 133

Text #8

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7094. Min Act: -0.0000

Data Index: 289445 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6772. Min Act: -0.0000

Data Index: 771912 (The Pile)

Max Activating Token Index: 193

Text #10

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1516739 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1488202 (The Pile)

Max Activating Token Index: 434

Text #12

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6955. Min Act: -0.0000

Data Index: 248174 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1496227 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1383625 (The Pile)

Max Activating Token Index: 645

Text #15

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6726. Min Act: -0.0000

Data Index: 246986 (The Pile)

Max Activating Token Index: 928

Text #16

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6959. Min Act: -0.0000

Data Index: 547370 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1727978 (The Pile)

Max Activating Token Index: 204

Text #18

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6632. Min Act: -0.0001

Data Index: 1449035 (The Pile)

Max Activating Token Index: 562

Text #19

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1816199 (The Pile)

Max Activating Token Index: 589