Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 174 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1263036 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1501538 (Python Code)

Max Activating Token Index: 735

Text #2

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0358. Min Act: -0.0001

Data Index: 631771 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0362. Min Act: -0.0001

Data Index: 527494 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0338. Min Act: -0.0002

Data Index: 834919 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0324. Min Act: -0.0002

Data Index: 999755 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0337. Min Act: -0.0002

Data Index: 626557 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0325. Min Act: -0.0002

Data Index: 600973 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0316. Min Act: -0.0001

Data Index: 109201 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0318. Min Act: -0.0002

Data Index: 20342 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0314. Min Act: -0.0002

Data Index: 852431 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0327. Min Act: -0.0001

Data Index: 830984 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0332. Min Act: -0.0001

Data Index: 990550 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0316. Min Act: -0.0002

Data Index: 853262 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1241657 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1032762 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0310. Min Act: -0.0002

Data Index: 444051 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1309485 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0319. Min Act: -0.0002

Data Index: 756020 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1022734 (C4 (Web Text))

Max Activating Token Index: 341