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

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

Neuron 1155 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7976. Min Act: -0.0003

Data Index: 573030 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7571. Min Act: -0.0003

Data Index: 85421 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7625. Min Act: -0.0002

Data Index: 348375 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7545. Min Act: -0.0002

Data Index: 967058 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7230. Min Act: -0.0002

Data Index: 1219489 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7312. Min Act: -0.0002

Data Index: 1068831 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7038. Min Act: -0.0002

Data Index: 762393 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6975. Min Act: -0.0002

Data Index: 629096 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6941. Min Act: -0.0002

Data Index: 412397 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6914. Min Act: -0.0002

Data Index: 1228648 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6712. Min Act: -0.0003

Data Index: 279647 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6880. Min Act: -0.0002

Data Index: 1346467 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6670. Min Act: -0.0002

Data Index: 382012 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6666. Min Act: -0.0002

Data Index: 117797 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6569. Min Act: -0.0002

Data Index: 722514 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6407. Min Act: -0.0002

Data Index: 335764 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6303. Min Act: -0.0002

Data Index: 94418 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6308. Min Act: -0.0002

Data Index: 440718 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6213. Min Act: -0.0002

Data Index: 876467 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6353. Min Act: -0.0002

Data Index: 716586 (C4 (Web Text))

Max Activating Token Index: 235