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

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

Neuron 1107 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: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: -0.0001

Data Index: 899379 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0435. Min Act: -0.0001

Data Index: 798232 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0442. Min Act: -0.0001

Data Index: 695599 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0472. Min Act: -0.0001

Data Index: 612408 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0430. Min Act: -0.0001

Data Index: 519059 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0375. Min Act: -0.0001

Data Index: 493483 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0403. Min Act: -0.0001

Data Index: 44806 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0349. Min Act: -0.0001

Data Index: 955883 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0394. Min Act: -0.0001

Data Index: 133200 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0394. Min Act: -0.0001

Data Index: 175585 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1222252 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0345. Min Act: -0.0001

Data Index: 662442 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0374. Min Act: -0.0001

Data Index: 671886 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0327. Min Act: -0.0001

Data Index: 359497 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0380. Min Act: -0.0001

Data Index: 455802 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0375. Min Act: -0.0001

Data Index: 440829 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0361. Min Act: -0.0001

Data Index: 232734 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0337. Min Act: -0.0001

Data Index: 1298574 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0369. Min Act: -0.0001

Data Index: 1028204 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1152272 (C4 (Web Text))

Max Activating Token Index: 169