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

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

Neuron 2595 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6781. Min Act: -0.0001

Data Index: 345242 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1419305 (Python Code)

Max Activating Token Index: 378

Text #2

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6568. Min Act: -0.0001

Data Index: 1466657 (Python Code)

Max Activating Token Index: 137

Text #3

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5561. Min Act: -0.0001

Data Index: 527613 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5285. Min Act: -0.0001

Data Index: 1618212 (Python Code)

Max Activating Token Index: 340

Text #5

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5153. Min Act: -0.0001

Data Index: 282543 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5003. Min Act: -0.0001

Data Index: 1127275 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5273. Min Act: -0.0001

Data Index: 1363651 (Python Code)

Max Activating Token Index: 987

Text #8

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5067. Min Act: -0.0001

Data Index: 313482 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4780. Min Act: -0.0001

Data Index: 1392551 (Python Code)

Max Activating Token Index: 501

Text #10

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4995. Min Act: -0.0001

Data Index: 621621 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4848. Min Act: -0.0001

Data Index: 996685 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4571. Min Act: -0.0001

Data Index: 1211639 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5130. Min Act: -0.0001

Data Index: 394124 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4826. Min Act: -0.0001

Data Index: 708906 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4596. Min Act: -0.0001

Data Index: 849303 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4358. Min Act: -0.0001

Data Index: 1045080 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4750. Min Act: -0.0001

Data Index: 332398 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4709. Min Act: -0.0001

Data Index: 1183056 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4622. Min Act: -0.0001

Data Index: 441220 (C4 (Web Text))

Max Activating Token Index: 212