Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3931 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.4021. Min Range: -3.4021

Max Act: 3.4021. Min Act: -0.0001

Data Index: 1391174 (Python Code)

Max Activating Token Index: 702

Text #1

Max Range: 3.4021. Min Range: -3.4021

Max Act: 3.2036. Min Act: -0.0001

Data Index: 1374231 (Python Code)

Max Activating Token Index: 306

Text #2

Max Range: 3.4021. Min Range: -3.4021

Max Act: 3.0973. Min Act: -0.0000

Data Index: 1471293 (Python Code)

Max Activating Token Index: 713

Text #3

Max Range: 3.4021. Min Range: -3.4021

Max Act: 3.0116. Min Act: -0.0001

Data Index: 1554552 (Python Code)

Max Activating Token Index: 480

Text #4

Max Range: 3.4021. Min Range: -3.4021

Max Act: 2.4971. Min Act: -0.0001

Data Index: 1606135 (Python Code)

Max Activating Token Index: 705

Text #5

Max Range: 3.4021. Min Range: -3.4021

Max Act: 2.9596. Min Act: -0.0001

Data Index: 1484739 (Python Code)

Max Activating Token Index: 217

Text #6

Max Range: 3.4021. Min Range: -3.4021

Max Act: 2.6467. Min Act: -0.0001

Data Index: 1430363 (Python Code)

Max Activating Token Index: 453

Text #7

Max Range: 3.4021. Min Range: -3.4021

Max Act: 2.5632. Min Act: -0.0001

Data Index: 1418403 (Python Code)

Max Activating Token Index: 209

Text #8

Max Range: 3.4021. Min Range: -3.4021

Max Act: 2.5248. Min Act: -0.0000

Data Index: 1573995 (Python Code)

Max Activating Token Index: 612

Text #9

Max Range: 3.4021. Min Range: -3.4021

Max Act: 2.5219. Min Act: -0.0001

Data Index: 1651203 (Python Code)

Max Activating Token Index: 667

Text #10

Max Range: 3.4021. Min Range: -3.4021

Max Act: 2.0509. Min Act: -0.0001

Data Index: 1617592 (Python Code)

Max Activating Token Index: 568

Text #11

Max Range: 3.4021. Min Range: -3.4021

Max Act: 2.5229. Min Act: -0.0001

Data Index: 1448705 (Python Code)

Max Activating Token Index: 385

Text #12

Max Range: 3.4021. Min Range: -3.4021

Max Act: 2.3380. Min Act: -0.0000

Data Index: 1478638 (Python Code)

Max Activating Token Index: 384

Text #13

Max Range: 3.4021. Min Range: -3.4021

Max Act: 2.1059. Min Act: -0.0001

Data Index: 1362788 (Python Code)

Max Activating Token Index: 469

Text #14

Max Range: 3.4021. Min Range: -3.4021

Max Act: 2.0429. Min Act: -0.0001

Data Index: 1600870 (Python Code)

Max Activating Token Index: 405

Text #15

Max Range: 3.4021. Min Range: -3.4021

Max Act: 1.7857. Min Act: -0.0001

Data Index: 1423652 (Python Code)

Max Activating Token Index: 781

Text #16

Max Range: 3.4021. Min Range: -3.4021

Max Act: 1.8710. Min Act: -0.0001

Data Index: 1404873 (Python Code)

Max Activating Token Index: 251

Text #17

Max Range: 3.4021. Min Range: -3.4021

Max Act: 1.9860. Min Act: -0.0001

Data Index: 1492307 (Python Code)

Max Activating Token Index: 222

Text #18

Max Range: 3.4021. Min Range: -3.4021

Max Act: 1.8559. Min Act: -0.0000

Data Index: 1519820 (Python Code)

Max Activating Token Index: 570

Text #19

Max Range: 3.4021. Min Range: -3.4021

Max Act: 1.8853. Min Act: -0.0000

Data Index: 1573233 (Python Code)

Max Activating Token Index: 149