Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1059 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.7337. Min Act: -0.0003

Data Index: 36006 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5730. Min Act: -0.0003

Data Index: 229395 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5910. Min Act: -0.0003

Data Index: 76475 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5677. Min Act: -0.0003

Data Index: 461743 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5608. Min Act: -0.0003

Data Index: 899572 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5401. Min Act: -0.0003

Data Index: 1264888 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5613. Min Act: -0.0003

Data Index: 1098824 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5551. Min Act: -0.0003

Data Index: 980526 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5379. Min Act: -0.0003

Data Index: 1061647 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5427. Min Act: -0.0003

Data Index: 1270854 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5168. Min Act: -0.0003

Data Index: 1312513 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5116. Min Act: -0.0003

Data Index: 930087 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5027. Min Act: -0.0003

Data Index: 19680 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5019. Min Act: -0.0003

Data Index: 1070411 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5101. Min Act: -0.0003

Data Index: 622934 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4936. Min Act: -0.0003

Data Index: 591012 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4917. Min Act: -0.0003

Data Index: 419129 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4869. Min Act: -0.0002

Data Index: 31748 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4982. Min Act: -0.0003

Data Index: 738167 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4825. Min Act: -0.0003

Data Index: 9362 (C4 (Web Text))

Max Activating Token Index: 722