Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4789 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.9514. Min Act: -0.0000

Data Index: 56518 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.9156. Min Act: -0.0000

Data Index: 59322 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8855. Min Act: -0.0000

Data Index: 504476 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8550. Min Act: 0.0000

Data Index: 187798 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8673. Min Act: -0.0000

Data Index: 342782 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8501. Min Act: -0.0000

Data Index: 1379578 (Python Code)

Max Activating Token Index: 222

Text #6

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8397. Min Act: -0.0000

Data Index: 908407 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7843. Min Act: -0.0000

Data Index: 856583 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8098. Min Act: 0.0000

Data Index: 681640 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7822. Min Act: -0.0000

Data Index: 894452 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7748. Min Act: -0.0000

Data Index: 153707 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1204550 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7718. Min Act: -0.0000

Data Index: 333644 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7126. Min Act: -0.0000

Data Index: 403544 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7381. Min Act: 0.0000

Data Index: 1000776 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1046829 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1037945 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.6544. Min Act: -0.0000

Data Index: 317334 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.6607. Min Act: -0.0000

Data Index: 136662 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.6801. Min Act: 0.0000

Data Index: 237417 (C4 (Web Text))

Max Activating Token Index: 496