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

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

Neuron 5304 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0781. Min Act: -0.0000

Data Index: 45255 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0470. Min Act: -0.0000

Data Index: 324458 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0481. Min Act: -0.0000

Data Index: 116229 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0453. Min Act: -0.0000

Data Index: 333831 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0443. Min Act: -0.0000

Data Index: 1279820 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0480. Min Act: -0.0000

Data Index: 570062 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0386. Min Act: -0.0000

Data Index: 1484224 (Python Code)

Max Activating Token Index: 970

Text #7

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0391. Min Act: -0.0000

Data Index: 1164017 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0433. Min Act: -0.0000

Data Index: 994131 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0337. Min Act: -0.0000

Data Index: 67972 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0365. Min Act: -0.0000

Data Index: 1196630 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0416. Min Act: -0.0000

Data Index: 870023 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0372. Min Act: -0.0000

Data Index: 647383 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0356. Min Act: -0.0000

Data Index: 300956 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0308. Min Act: -0.0000

Data Index: 9837 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0351. Min Act: -0.0000

Data Index: 192228 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0298. Min Act: -0.0000

Data Index: 1164763 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0349. Min Act: -0.0000

Data Index: 982172 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0333. Min Act: -0.0000

Data Index: 1326403 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0356. Min Act: -0.0000

Data Index: 1341121 (C4 (Web Text))

Max Activating Token Index: 427