Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 468 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1298723 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0436. Min Act: -0.0001

Data Index: 826301 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0433. Min Act: -0.0001

Data Index: 340761 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0396. Min Act: -0.0001

Data Index: 123111 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1061270 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1230197 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0387. Min Act: -0.0001

Data Index: 1005369 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0377. Min Act: -0.0001

Data Index: 146629 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0382. Min Act: -0.0001

Data Index: 664140 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1296721 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0373. Min Act: -0.0001

Data Index: 275822 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0371. Min Act: -0.0001

Data Index: 520235 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0355. Min Act: -0.0001

Data Index: 967955 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0375. Min Act: -0.0001

Data Index: 6635 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0357. Min Act: -0.0001

Data Index: 168074 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0362. Min Act: -0.0001

Data Index: 91774 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0344. Min Act: -0.0001

Data Index: 94116 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0361. Min Act: -0.0001

Data Index: 688789 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0353. Min Act: -0.0001

Data Index: 744367 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1291852 (C4 (Web Text))

Max Activating Token Index: 84