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

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

Neuron 3108 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: 1.8126. Min Range: -1.8126

Max Act: 1.8126. Min Act: -0.0000

Data Index: 1018141 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.6620. Min Act: -0.0000

Data Index: 390554 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.6057. Min Act: -0.0000

Data Index: 1123583 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.6867. Min Act: -0.0000

Data Index: 274472 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.5310. Min Act: -0.0000

Data Index: 144055 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.3998. Min Act: -0.0000

Data Index: 965666 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.3854. Min Act: -0.0000

Data Index: 324640 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.4528. Min Act: -0.0000

Data Index: 17722 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.3467. Min Act: -0.0000

Data Index: 99380 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.3312. Min Act: -0.0000

Data Index: 563571 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.2411. Min Act: -0.0000

Data Index: 188126 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.2737. Min Act: -0.0000

Data Index: 504790 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.2306. Min Act: -0.0000

Data Index: 173512 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.1447. Min Act: -0.0000

Data Index: 856221 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.1387. Min Act: -0.0000

Data Index: 489811 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.1253. Min Act: -0.0000

Data Index: 37424 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.1837. Min Act: -0.0000

Data Index: 91007 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.1843. Min Act: -0.0000

Data Index: 300595 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.1646. Min Act: -0.0000

Data Index: 776867 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 1.8126. Min Range: -1.8126

Max Act: 1.2370. Min Act: -0.0000

Data Index: 111965 (C4 (Web Text))

Max Activating Token Index: 47