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

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

Neuron 1053 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: 0.0483. Min Range: -0.0483

Max Act: 0.0483. Min Act: -0.0001

Data Index: 479024 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1379993 (Python Code)

Max Activating Token Index: 520

Text #2

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0436. Min Act: -0.0001

Data Index: 282064 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0458. Min Act: -0.0001

Data Index: 792786 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0437. Min Act: -0.0001

Data Index: 11951 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0423. Min Act: -0.0001

Data Index: 76899 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0427. Min Act: -0.0001

Data Index: 32148 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1595376 (Python Code)

Max Activating Token Index: 575

Text #8

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0398. Min Act: -0.0001

Data Index: 1399725 (Python Code)

Max Activating Token Index: 856

Text #9

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1330055 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0371. Min Act: -0.0001

Data Index: 573677 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0418. Min Act: -0.0001

Data Index: 794112 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0388. Min Act: -0.0001

Data Index: 1382106 (Python Code)

Max Activating Token Index: 533

Text #13

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1478883 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0396. Min Act: -0.0001

Data Index: 629758 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0380. Min Act: -0.0001

Data Index: 782969 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1517712 (Python Code)

Max Activating Token Index: 676

Text #17

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1638795 (Python Code)

Max Activating Token Index: 673

Text #18

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1333267 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1196267 (C4 (Web Text))

Max Activating Token Index: 15