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

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

Neuron 1758 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: 1.7218. Min Range: -1.7218

Max Act: 1.7218. Min Act: -0.0000

Data Index: 1180696 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.5346. Min Act: -0.0000

Data Index: 1095002 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.5498. Min Act: -0.0000

Data Index: 1014161 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.5686. Min Act: -0.0000

Data Index: 203052 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6107. Min Act: -0.0000

Data Index: 1062704 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.5074. Min Act: -0.0000

Data Index: 247186 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.3689. Min Act: -0.0000

Data Index: 163675 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.5598. Min Act: -0.0000

Data Index: 536876 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4526. Min Act: -0.0000

Data Index: 256584 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4414. Min Act: -0.0000

Data Index: 671115 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.5199. Min Act: -0.0000

Data Index: 138456 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4233. Min Act: -0.0000

Data Index: 14333 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4847. Min Act: -0.0000

Data Index: 93073 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.3557. Min Act: -0.0000

Data Index: 1066244 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4676. Min Act: -0.0000

Data Index: 335290 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4147. Min Act: -0.0000

Data Index: 757191 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.3839. Min Act: -0.0000

Data Index: 288715 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4293. Min Act: -0.0000

Data Index: 801262 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.3716. Min Act: -0.0000

Data Index: 1127555 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.3282. Min Act: -0.0000

Data Index: 1341101 (C4 (Web Text))

Max Activating Token Index: 388