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

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

Neuron 4185 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: 1.0090. Min Range: -1.0090

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1260146 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9657. Min Act: -0.0000

Data Index: 326359 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8789. Min Act: -0.0000

Data Index: 991085 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1182235 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8937. Min Act: -0.0000

Data Index: 17894 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8815. Min Act: -0.0000

Data Index: 343316 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8256. Min Act: -0.0000

Data Index: 844627 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8464. Min Act: -0.0000

Data Index: 169537 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7915. Min Act: -0.0000

Data Index: 311535 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1432590 (Python Code)

Max Activating Token Index: 505

Text #10

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1214205 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1315021 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7372. Min Act: -0.0000

Data Index: 301768 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7376. Min Act: -0.0000

Data Index: 800702 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.6872. Min Act: -0.0000

Data Index: 551784 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7307. Min Act: -0.0000

Data Index: 164318 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7201. Min Act: -0.0000

Data Index: 22306 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7184. Min Act: -0.0000

Data Index: 658381 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7053. Min Act: -0.0000

Data Index: 851498 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7057. Min Act: -0.0000

Data Index: 393092 (C4 (Web Text))

Max Activating Token Index: 872