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

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

Neuron 913 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.5144. Min Act: -0.0000

Data Index: 1342499 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.3973. Min Act: -0.0000

Data Index: 932795 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.2813. Min Act: -0.0000

Data Index: 337352 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.3406. Min Act: -0.0000

Data Index: 1126146 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.2061. Min Act: -0.0000

Data Index: 124483 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.3116. Min Act: -0.0000

Data Index: 542718 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.2331. Min Act: -0.0000

Data Index: 637156 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.2209. Min Act: -0.0000

Data Index: 748311 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.1666. Min Act: -0.0000

Data Index: 175311 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.1602. Min Act: -0.0000

Data Index: 645616 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.3070. Min Act: -0.0000

Data Index: 583451 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.2885. Min Act: -0.0000

Data Index: 502486 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.1453. Min Act: -0.0000

Data Index: 430203 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.0948. Min Act: -0.0000

Data Index: 680192 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1019322 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.0827. Min Act: -0.0000

Data Index: 1306156 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.1148. Min Act: -0.0000

Data Index: 249248 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.1045. Min Act: -0.0000

Data Index: 678290 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1126684 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 1.5144. Min Range: -1.5144

Max Act: 1.0993. Min Act: -0.0000

Data Index: 312608 (C4 (Web Text))

Max Activating Token Index: 500