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

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

Neuron 2434 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0481. Min Act: -0.0003

Data Index: 175396 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0468. Min Act: -0.0003

Data Index: 968139 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0432. Min Act: -0.0003

Data Index: 354674 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0460. Min Act: -0.0003

Data Index: 343966 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1249323 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1262695 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0422. Min Act: -0.0003

Data Index: 479363 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0433. Min Act: -0.0003

Data Index: 280381 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0412. Min Act: -0.0003

Data Index: 40339 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0423. Min Act: -0.0003

Data Index: 235301 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0415. Min Act: -0.0003

Data Index: 668315 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1337958 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0429. Min Act: -0.0003

Data Index: 545363 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1005048 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0415. Min Act: -0.0003

Data Index: 882799 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0398. Min Act: -0.0003

Data Index: 743897 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1042527 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1251107 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0403. Min Act: -0.0002

Data Index: 987395 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0403. Min Act: -0.0003

Data Index: 76105 (C4 (Web Text))

Max Activating Token Index: 502