Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1854 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.9129. Min Act: -0.0001

Data Index: 92254 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.9523. Min Act: -0.0001

Data Index: 871320 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.6715. Min Act: -0.0001

Data Index: 1034829 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.7827. Min Act: -0.0001

Data Index: 854123 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.6468. Min Act: -0.0001

Data Index: 586990 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.1316. Min Act: -0.0001

Data Index: 1014440 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.4400. Min Act: -0.0001

Data Index: 573255 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.5488. Min Act: -0.0001

Data Index: 388472 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.4981. Min Act: -0.0001

Data Index: 636374 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.4643. Min Act: -0.0001

Data Index: 211787 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.3589. Min Act: -0.0001

Data Index: 352715 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.2012. Min Act: -0.0001

Data Index: 902567 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.1152. Min Act: -0.0001

Data Index: 228540 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.1489. Min Act: -0.0001

Data Index: 195681 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.1967. Min Act: -0.0001

Data Index: 231574 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.1068. Min Act: -0.0001

Data Index: 486568 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.2460. Min Act: -0.0001

Data Index: 709765 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 2.9523. Min Range: -2.9523

Max Act: 1.9220. Min Act: -0.0001

Data Index: 1223851 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 2.9523. Min Range: -2.9523

Max Act: 2.1776. Min Act: -0.0001

Data Index: 768418 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 2.9523. Min Range: -2.9523

Max Act: 1.8536. Min Act: -0.0001

Data Index: 506120 (C4 (Web Text))

Max Activating Token Index: 694