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

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

Neuron 4418 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7246. Min Range: -2.7246

Max Act: 2.7246. Min Act: -0.0000

Data Index: 975533 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 2.7246. Min Range: -2.7246

Max Act: 2.2841. Min Act: -0.0000

Data Index: 130091 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.9129. Min Act: -0.0000

Data Index: 290114 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 2.7246. Min Range: -2.7246

Max Act: 2.0123. Min Act: -0.0000

Data Index: 263163 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 2.7246. Min Range: -2.7246

Max Act: 2.0000. Min Act: -0.0000

Data Index: 372852 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 2.7246. Min Range: -2.7246

Max Act: 2.0034. Min Act: -0.0001

Data Index: 496627 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.8773. Min Act: -0.0001

Data Index: 249497 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.8950. Min Act: -0.0001

Data Index: 1141755 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 2.7246. Min Range: -2.7246

Max Act: 2.0184. Min Act: -0.0000

Data Index: 681275 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.6811. Min Act: -0.0000

Data Index: 368443 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.7642. Min Act: -0.0001

Data Index: 727850 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.6389. Min Act: -0.0000

Data Index: 651047 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.7159. Min Act: -0.0000

Data Index: 601069 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.6760. Min Act: -0.0000

Data Index: 1218408 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.5545. Min Act: -0.0001

Data Index: 879562 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.6565. Min Act: -0.0000

Data Index: 919436 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.6885. Min Act: -0.0000

Data Index: 1169117 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.7258. Min Act: -0.0000

Data Index: 1310040 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.6473. Min Act: -0.0000

Data Index: 459485 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 2.7246. Min Range: -2.7246

Max Act: 1.5131. Min Act: -0.0000

Data Index: 830993 (C4 (Web Text))

Max Activating Token Index: 232