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

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

Neuron 503 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0414. Min Act: -0.0001

Data Index: 1116273 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0528. Min Act: -0.0001

Data Index: 67986 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1072315 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0505. Min Act: -0.0001

Data Index: 47829 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1548217 (Python Code)

Max Activating Token Index: 972

Text #5

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0376. Min Act: -0.0001

Data Index: 908101 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0454. Min Act: -0.0001

Data Index: 1364855 (Python Code)

Max Activating Token Index: 663

Text #7

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1523038 (Python Code)

Max Activating Token Index: 640

Text #8

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0369. Min Act: -0.0001

Data Index: 1550730 (Python Code)

Max Activating Token Index: 741

Text #9

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0405. Min Act: -0.0002

Data Index: 113043 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0458. Min Act: -0.0001

Data Index: 502057 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0382. Min Act: -0.0001

Data Index: 797466 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1596140 (Python Code)

Max Activating Token Index: 105

Text #13

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0423. Min Act: -0.0001

Data Index: 546983 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0395. Min Act: -0.0001

Data Index: 1204521 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0394. Min Act: -0.0001

Data Index: 582498 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1487666 (Python Code)

Max Activating Token Index: 576

Text #17

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0320. Min Act: -0.0001

Data Index: 902126 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0342. Min Act: -0.0002

Data Index: 853464 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0565. Min Act: -0.0001

Data Index: 411888 (C4 (Web Text))

Max Activating Token Index: 851