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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2842 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7903. Min Range: -2.7903

Max Act: 2.7903. Min Act: -0.0000

Data Index: 684721 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 2.7903. Min Range: -2.7903

Max Act: 2.7163. Min Act: -0.0000

Data Index: 947043 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 2.7903. Min Range: -2.7903

Max Act: 2.5264. Min Act: -0.0000

Data Index: 515856 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 2.7903. Min Range: -2.7903

Max Act: 2.2813. Min Act: -0.0000

Data Index: 36393 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 2.7903. Min Range: -2.7903

Max Act: 2.1430. Min Act: -0.0000

Data Index: 599559 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 2.7903. Min Range: -2.7903

Max Act: 2.0267. Min Act: -0.0000

Data Index: 252752 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 2.7903. Min Range: -2.7903

Max Act: 2.1178. Min Act: -0.0000

Data Index: 866770 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 2.7903. Min Range: -2.7903

Max Act: 2.0835. Min Act: -0.0000

Data Index: 340360 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 2.7903. Min Range: -2.7903

Max Act: 2.0030. Min Act: -0.0000

Data Index: 1065664 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 2.7903. Min Range: -2.7903

Max Act: 2.0042. Min Act: -0.0000

Data Index: 1049391 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 2.7903. Min Range: -2.7903

Max Act: 1.9534. Min Act: -0.0000

Data Index: 1247929 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 2.7903. Min Range: -2.7903

Max Act: 1.9533. Min Act: -0.0000

Data Index: 719957 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 2.7903. Min Range: -2.7903

Max Act: 1.9002. Min Act: -0.0000

Data Index: 518362 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 2.7903. Min Range: -2.7903

Max Act: 2.0009. Min Act: -0.0000

Data Index: 289458 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 2.7903. Min Range: -2.7903

Max Act: 1.8892. Min Act: -0.0000

Data Index: 559598 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.7903. Min Range: -2.7903

Max Act: 1.9717. Min Act: -0.0000

Data Index: 1062041 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 2.7903. Min Range: -2.7903

Max Act: 1.8715. Min Act: -0.0000

Data Index: 307433 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 2.7903. Min Range: -2.7903

Max Act: 1.8836. Min Act: -0.0000

Data Index: 1302886 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 2.7903. Min Range: -2.7903

Max Act: 1.8405. Min Act: -0.0000

Data Index: 442322 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 2.7903. Min Range: -2.7903

Max Act: 2.0507. Min Act: -0.0000

Data Index: 337550 (C4 (Web Text))

Max Activating Token Index: 901