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

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

Neuron 3968 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3478. Min Range: -2.3478

Max Act: 2.3478. Min Act: -0.0000

Data Index: 152637 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 2.3478. Min Range: -2.3478

Max Act: 2.0107. Min Act: -0.0000

Data Index: 1158447 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.8566. Min Act: -0.0000

Data Index: 795765 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.6424. Min Act: -0.0000

Data Index: 770177 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.6436. Min Act: -0.0000

Data Index: 106108 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.8266. Min Act: -0.0000

Data Index: 1281694 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.7583. Min Act: -0.0000

Data Index: 100450 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.6498. Min Act: -0.0000

Data Index: 292597 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.7118. Min Act: -0.0000

Data Index: 1350746 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.7643. Min Act: -0.0000

Data Index: 120677 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.6608. Min Act: -0.0000

Data Index: 80185 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.5993. Min Act: -0.0000

Data Index: 1109017 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.5775. Min Act: -0.0000

Data Index: 1303725 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.6247. Min Act: -0.0000

Data Index: 870407 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.5252. Min Act: -0.0000

Data Index: 535567 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1208677 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.6023. Min Act: -0.0000

Data Index: 835876 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.4574. Min Act: -0.0000

Data Index: 422476 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.4004. Min Act: -0.0000

Data Index: 186217 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 2.3478. Min Range: -2.3478

Max Act: 1.3916. Min Act: -0.0000

Data Index: 488172 (C4 (Web Text))

Max Activating Token Index: 727