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

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

Neuron 2006 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.6796. Min Act: -0.0000

Data Index: 578553 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5398. Min Act: -0.0000

Data Index: 496741 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1118530 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5401. Min Act: -0.0000

Data Index: 439845 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5120. Min Act: -0.0000

Data Index: 200883 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4765. Min Act: -0.0000

Data Index: 750405 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4594. Min Act: -0.0000

Data Index: 628780 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1143842 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1263021 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4501. Min Act: -0.0000

Data Index: 12723 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1136326 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4516. Min Act: -0.0000

Data Index: 379650 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4666. Min Act: 0.0000

Data Index: 925909 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4383. Min Act: -0.0000

Data Index: 847782 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4365. Min Act: -0.0000

Data Index: 120014 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1152515 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4305. Min Act: -0.0000

Data Index: 615325 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1311981 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4244. Min Act: -0.0000

Data Index: 525197 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4371. Min Act: -0.0000

Data Index: 417364 (C4 (Web Text))

Max Activating Token Index: 168