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

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

Neuron 5816 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: 1.8850. Min Range: -1.8850

Max Act: 1.8850. Min Act: -0.0000

Data Index: 443537 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.5216. Min Act: -0.0000

Data Index: 1135838 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4794. Min Act: -0.0000

Data Index: 766647 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4956. Min Act: -0.0000

Data Index: 246468 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4917. Min Act: -0.0000

Data Index: 260399 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3989. Min Act: -0.0000

Data Index: 264357 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4701. Min Act: -0.0000

Data Index: 272395 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.5576. Min Act: -0.0000

Data Index: 853258 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4276. Min Act: -0.0000

Data Index: 1249390 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4337. Min Act: -0.0000

Data Index: 813788 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4222. Min Act: -0.0000

Data Index: 184047 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3977. Min Act: -0.0000

Data Index: 19992 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4042. Min Act: -0.0000

Data Index: 1359769 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4012. Min Act: -0.0000

Data Index: 242723 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3852. Min Act: -0.0000

Data Index: 10182 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.2779. Min Act: -0.0000

Data Index: 747415 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3557. Min Act: -0.0000

Data Index: 989288 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.2599. Min Act: -0.0000

Data Index: 128612 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3409. Min Act: -0.0000

Data Index: 276332 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3156. Min Act: -0.0000

Data Index: 1300330 (C4 (Web Text))

Max Activating Token Index: 582