Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2121 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.7235. Min Act: -0.0000

Data Index: 49490 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.8594. Min Act: -0.0000

Data Index: 760917 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.0229. Min Act: -0.0000

Data Index: 763414 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1262604 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.8176. Min Act: -0.0001

Data Index: 648166 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1312433 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.5303. Min Act: -0.0000

Data Index: 413484 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1063172 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.5131. Min Act: -0.0000

Data Index: 604811 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.5120. Min Act: -0.0000

Data Index: 924668 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.4996. Min Act: -0.0000

Data Index: 519793 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.4447. Min Act: -0.0000

Data Index: 136292 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.4811. Min Act: -0.0000

Data Index: 474356 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.4521. Min Act: -0.0000

Data Index: 321835 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.4905. Min Act: -0.0001

Data Index: 284824 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.4737. Min Act: -0.0000

Data Index: 30445 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.4452. Min Act: -0.0000

Data Index: 191670 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.3387. Min Act: -0.0001

Data Index: 184925 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.4096. Min Act: -0.0000

Data Index: 756652 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.8594. Min Range: -0.8594

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1346827 (C4 (Web Text))

Max Activating Token Index: 283