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

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

Neuron 5280 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7163. Min Range: -2.7163

Max Act: 2.7163. Min Act: -0.0000

Data Index: 1176970 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 2.7163. Min Range: -2.7163

Max Act: 2.5380. Min Act: -0.0000

Data Index: 1349954 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 2.7163. Min Range: -2.7163

Max Act: 2.3429. Min Act: -0.0000

Data Index: 1273265 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 2.7163. Min Range: -2.7163

Max Act: 2.2176. Min Act: -0.0000

Data Index: 723545 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 2.7163. Min Range: -2.7163

Max Act: 2.1906. Min Act: -0.0000

Data Index: 1172060 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 2.7163. Min Range: -2.7163

Max Act: 2.2510. Min Act: -0.0000

Data Index: 1305907 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 2.7163. Min Range: -2.7163

Max Act: 2.1911. Min Act: -0.0000

Data Index: 1228662 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 2.7163. Min Range: -2.7163

Max Act: 2.1437. Min Act: -0.0000

Data Index: 74350 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 2.7163. Min Range: -2.7163

Max Act: 2.1127. Min Act: -0.0000

Data Index: 480617 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 2.7163. Min Range: -2.7163

Max Act: 2.0973. Min Act: -0.0000

Data Index: 1205302 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 2.7163. Min Range: -2.7163

Max Act: 2.1082. Min Act: -0.0000

Data Index: 1373712 (Python Code)

Max Activating Token Index: 411

Text #11

Max Range: 2.7163. Min Range: -2.7163

Max Act: 2.1642. Min Act: -0.0000

Data Index: 866445 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 2.7163. Min Range: -2.7163

Max Act: 1.9933. Min Act: -0.0000

Data Index: 14467 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 2.7163. Min Range: -2.7163

Max Act: 1.9170. Min Act: -0.0000

Data Index: 1307490 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 2.7163. Min Range: -2.7163

Max Act: 1.8955. Min Act: 0.0000

Data Index: 1118496 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 2.7163. Min Range: -2.7163

Max Act: 1.8606. Min Act: -0.0000

Data Index: 643836 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 2.7163. Min Range: -2.7163

Max Act: 1.7378. Min Act: -0.0000

Data Index: 1168186 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 2.7163. Min Range: -2.7163

Max Act: 1.8144. Min Act: -0.0000

Data Index: 612778 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 2.7163. Min Range: -2.7163

Max Act: 1.8915. Min Act: -0.0000

Data Index: 582867 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 2.7163. Min Range: -2.7163

Max Act: 1.6902. Min Act: -0.0000

Data Index: 1523347 (Python Code)

Max Activating Token Index: 287