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

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

Neuron 4628 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.9245. Min Act: -0.0000

Data Index: 611157 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.7879. Min Act: -0.0000

Data Index: 295024 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.9911. Min Act: -0.0000

Data Index: 712499 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.7971. Min Act: -0.0000

Data Index: 296072 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.6902. Min Act: -0.0000

Data Index: 1335699 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.6708. Min Act: -0.0000

Data Index: 261153 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.5480. Min Act: -0.0000

Data Index: 427253 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.6351. Min Act: -0.0000

Data Index: 1056561 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.5209. Min Act: -0.0000

Data Index: 918428 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.3588. Min Act: -0.0000

Data Index: 68401 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.4352. Min Act: -0.0000

Data Index: 988662 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.4125. Min Act: -0.0000

Data Index: 26896 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.3282. Min Act: -0.0000

Data Index: 580151 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.4513. Min Act: -0.0000

Data Index: 19557 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1327346 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.3052. Min Act: -0.0000

Data Index: 135102 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.2897. Min Act: -0.0000

Data Index: 59627 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.2747. Min Act: -0.0000

Data Index: 126730 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.2415. Min Act: -0.0000

Data Index: 800016 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 1.9911. Min Range: -1.9911

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1211640 (C4 (Web Text))

Max Activating Token Index: 106