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

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

Neuron 2767 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4314. Min Range: -2.4314

Max Act: 2.4314. Min Act: -0.0000

Data Index: 1023690 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 2.4314. Min Range: -2.4314

Max Act: 2.2937. Min Act: -0.0000

Data Index: 1508407 (Python Code)

Max Activating Token Index: 604

Text #2

Max Range: 2.4314. Min Range: -2.4314

Max Act: 2.1717. Min Act: -0.0000

Data Index: 1506161 (Python Code)

Max Activating Token Index: 698

Text #3

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.9968. Min Act: -0.0000

Data Index: 1375224 (Python Code)

Max Activating Token Index: 848

Text #4

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.8528. Min Act: -0.0000

Data Index: 1370885 (Python Code)

Max Activating Token Index: 382

Text #5

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.9620. Min Act: -0.0000

Data Index: 103571 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.9457. Min Act: -0.0000

Data Index: 1558373 (Python Code)

Max Activating Token Index: 743

Text #7

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.9308. Min Act: -0.0000

Data Index: 1544230 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.8890. Min Act: -0.0000

Data Index: 1404691 (Python Code)

Max Activating Token Index: 615

Text #9

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.9751. Min Act: -0.0000

Data Index: 1400975 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.9333. Min Act: -0.0000

Data Index: 519550 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.8359. Min Act: -0.0000

Data Index: 1586398 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.8344. Min Act: -0.0000

Data Index: 1597105 (Python Code)

Max Activating Token Index: 783

Text #13

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.8213. Min Act: -0.0000

Data Index: 1409732 (Python Code)

Max Activating Token Index: 186

Text #14

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.8159. Min Act: -0.0000

Data Index: 1402980 (Python Code)

Max Activating Token Index: 855

Text #15

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.8174. Min Act: -0.0000

Data Index: 186478 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.9178. Min Act: -0.0000

Data Index: 1632343 (Python Code)

Max Activating Token Index: 297

Text #17

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.8124. Min Act: -0.0000

Data Index: 1362898 (Python Code)

Max Activating Token Index: 224

Text #18

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.7125. Min Act: -0.0000

Data Index: 1480312 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.9013. Min Act: -0.0000

Data Index: 1564320 (Python Code)

Max Activating Token Index: 658