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

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

Neuron 2409 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1134796 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7456. Min Act: -0.0000

Data Index: 474862 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6377. Min Act: -0.0000

Data Index: 914846 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1212637 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5625. Min Act: -0.0000

Data Index: 224712 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5500. Min Act: -0.0000

Data Index: 325533 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5492. Min Act: -0.0000

Data Index: 548482 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1460885 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.4811. Min Act: -0.0000

Data Index: 113141 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1068327 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5019. Min Act: -0.0000

Data Index: 551220 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5078. Min Act: -0.0000

Data Index: 400473 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1259816 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1190114 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.4829. Min Act: -0.0000

Data Index: 954257 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1301703 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.4638. Min Act: -0.0000

Data Index: 157391 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1378498 (Python Code)

Max Activating Token Index: 112

Text #18

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.4905. Min Act: -0.0000

Data Index: 543440 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.4798. Min Act: 0.0000

Data Index: 1331966 (C4 (Web Text))

Max Activating Token Index: 360