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

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

Neuron 1735 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1390320 (Python Code)

Max Activating Token Index: 260

Text #1

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1061589 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0501. Min Act: -0.0001

Data Index: 786436 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0479. Min Act: -0.0001

Data Index: 778633 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1380906 (Python Code)

Max Activating Token Index: 344

Text #5

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1380755 (Python Code)

Max Activating Token Index: 536

Text #6

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0482. Min Act: -0.0001

Data Index: 258836 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0518. Min Act: -0.0001

Data Index: 1384787 (Python Code)

Max Activating Token Index: 839

Text #8

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1421340 (Python Code)

Max Activating Token Index: 102

Text #9

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0410. Min Act: -0.0001

Data Index: 573573 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0405. Min Act: -0.0001

Data Index: 325443 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0429. Min Act: -0.0001

Data Index: 494363 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0429. Min Act: -0.0001

Data Index: 820062 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0427. Min Act: -0.0001

Data Index: 347139 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0407. Min Act: -0.0001

Data Index: 156072 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0413. Min Act: -0.0001

Data Index: 48331 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0431. Min Act: -0.0001

Data Index: 167213 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0412. Min Act: -0.0001

Data Index: 18693 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0420. Min Act: -0.0001

Data Index: 96450 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0415. Min Act: -0.0001

Data Index: 838208 (C4 (Web Text))

Max Activating Token Index: 925