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

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

Neuron 1995 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: 0.0403. Min Range: -0.0403

Max Act: 0.0403. Min Act: -0.0001

Data Index: 629122 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0372. Min Act: -0.0001

Data Index: 989762 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1265065 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0388. Min Act: -0.0001

Data Index: 1199990 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0380. Min Act: -0.0001

Data Index: 1130060 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0373. Min Act: -0.0001

Data Index: 73426 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0368. Min Act: -0.0001

Data Index: 545350 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0370. Min Act: -0.0001

Data Index: 730216 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0356. Min Act: -0.0001

Data Index: 120889 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0359. Min Act: -0.0001

Data Index: 918413 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0356. Min Act: -0.0001

Data Index: 921739 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1093270 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0352. Min Act: -0.0001

Data Index: 832688 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0359. Min Act: -0.0001

Data Index: 303254 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0354. Min Act: -0.0001

Data Index: 604117 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0352. Min Act: -0.0001

Data Index: 853530 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0356. Min Act: -0.0001

Data Index: 677456 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1308213 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0346. Min Act: -0.0001

Data Index: 241099 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0347. Min Act: -0.0001

Data Index: 195497 (C4 (Web Text))

Max Activating Token Index: 63