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

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

Neuron 5709 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2339. Min Range: -6.2339

Max Act: 6.2339. Min Act: -0.0000

Data Index: 389777 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 6.2339. Min Range: -6.2339

Max Act: 6.1842. Min Act: -0.0000

Data Index: 449132 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 6.2339. Min Range: -6.2339

Max Act: 5.9576. Min Act: -0.0000

Data Index: 369272 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 6.2339. Min Range: -6.2339

Max Act: 5.5299. Min Act: -0.0000

Data Index: 975576 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 6.2339. Min Range: -6.2339

Max Act: 5.4310. Min Act: -0.0000

Data Index: 237596 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 6.2339. Min Range: -6.2339

Max Act: 5.4294. Min Act: -0.0000

Data Index: 502275 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 6.2339. Min Range: -6.2339

Max Act: 5.4362. Min Act: -0.0000

Data Index: 1353691 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 6.2339. Min Range: -6.2339

Max Act: 5.3098. Min Act: -0.0000

Data Index: 1320883 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 6.2339. Min Range: -6.2339

Max Act: 4.8456. Min Act: -0.0000

Data Index: 105911 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 6.2339. Min Range: -6.2339

Max Act: 5.0003. Min Act: -0.0000

Data Index: 944785 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 6.2339. Min Range: -6.2339

Max Act: 4.7198. Min Act: -0.0000

Data Index: 1308036 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 6.2339. Min Range: -6.2339

Max Act: 5.2675. Min Act: -0.0000

Data Index: 51956 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 6.2339. Min Range: -6.2339

Max Act: 4.9029. Min Act: -0.0000

Data Index: 1584791 (Python Code)

Max Activating Token Index: 780

Text #13

Max Range: 6.2339. Min Range: -6.2339

Max Act: 4.8602. Min Act: -0.0000

Data Index: 908041 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 6.2339. Min Range: -6.2339

Max Act: 4.8918. Min Act: -0.0000

Data Index: 956081 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 6.2339. Min Range: -6.2339

Max Act: 4.5319. Min Act: -0.0000

Data Index: 314056 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 6.2339. Min Range: -6.2339

Max Act: 4.7185. Min Act: -0.0000

Data Index: 379580 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 6.2339. Min Range: -6.2339

Max Act: 4.8374. Min Act: -0.0000

Data Index: 949551 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 6.2339. Min Range: -6.2339

Max Act: 4.8135. Min Act: -0.0000

Data Index: 626685 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 6.2339. Min Range: -6.2339

Max Act: 4.8149. Min Act: -0.0000

Data Index: 207003 (C4 (Web Text))

Max Activating Token Index: 641