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

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

Neuron 4327 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.5049. Min Act: 0.0000

Data Index: 60227 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.5523. Min Act: -0.0000

Data Index: 354757 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1183230 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.5290. Min Act: -0.0000

Data Index: 600495 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.5248. Min Act: -0.0000

Data Index: 332837 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.5450. Min Act: -0.0000

Data Index: 653558 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1344115 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4309. Min Act: -0.0000

Data Index: 547800 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1321052 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1253643 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3995. Min Act: -0.0000

Data Index: 581696 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4278. Min Act: -0.0000

Data Index: 381932 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1332508 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1329201 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4128. Min Act: -0.0000

Data Index: 378767 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.4022. Min Act: -0.0000

Data Index: 340725 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3986. Min Act: -0.0000

Data Index: 950506 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3762. Min Act: -0.0000

Data Index: 977100 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1075343 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.5523. Min Range: -0.5523

Max Act: 0.3709. Min Act: -0.0000

Data Index: 19264 (C4 (Web Text))

Max Activating Token Index: 537