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

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

Neuron 4652 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3374. Min Range: -2.3374

Max Act: 2.3374. Min Act: -0.0000

Data Index: 1100990 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 2.3374. Min Range: -2.3374

Max Act: 2.2178. Min Act: -0.0000

Data Index: 492391 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 2.3374. Min Range: -2.3374

Max Act: 2.1215. Min Act: -0.0000

Data Index: 437534 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 2.3374. Min Range: -2.3374

Max Act: 2.0697. Min Act: -0.0000

Data Index: 501408 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 2.3374. Min Range: -2.3374

Max Act: 2.0558. Min Act: -0.0000

Data Index: 35402 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.9176. Min Act: -0.0000

Data Index: 910444 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.8806. Min Act: -0.0000

Data Index: 1062574 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.8592. Min Act: -0.0000

Data Index: 195974 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.8256. Min Act: -0.0000

Data Index: 78773 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.7354. Min Act: -0.0000

Data Index: 570638 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.6354. Min Act: -0.0000

Data Index: 617584 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.8914. Min Act: -0.0000

Data Index: 506886 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.7958. Min Act: -0.0000

Data Index: 275995 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.6913. Min Act: -0.0000

Data Index: 695565 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.6815. Min Act: -0.0000

Data Index: 673211 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.7770. Min Act: -0.0000

Data Index: 1315213 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.8477. Min Act: -0.0000

Data Index: 1030516 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.8524. Min Act: -0.0000

Data Index: 740877 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.8391. Min Act: -0.0000

Data Index: 576637 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.7305. Min Act: -0.0000

Data Index: 661448 (C4 (Web Text))

Max Activating Token Index: 667