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

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

Neuron 5356 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0610. Min Act: -0.0002

Data Index: 612418 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0464. Min Act: -0.0002

Data Index: 347963 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0440. Min Act: -0.0002

Data Index: 330871 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0432. Min Act: -0.0002

Data Index: 791762 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0406. Min Act: -0.0002

Data Index: 192341 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1258315 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0422. Min Act: -0.0002

Data Index: 218372 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0386. Min Act: -0.0002

Data Index: 532539 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0375. Min Act: -0.0002

Data Index: 135723 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0377. Min Act: -0.0002

Data Index: 302045 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0381. Min Act: -0.0002

Data Index: 256750 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1025457 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0362. Min Act: -0.0002

Data Index: 407431 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1160082 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0365. Min Act: -0.0002

Data Index: 326344 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1033042 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0347. Min Act: -0.0002

Data Index: 671446 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0351. Min Act: -0.0002

Data Index: 877995 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0348. Min Act: -0.0002

Data Index: 313488 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0355. Min Act: -0.0002

Data Index: 321619 (C4 (Web Text))

Max Activating Token Index: 558