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

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

Neuron 2378 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.8254. Min Act: -0.0001

Data Index: 1408572 (Python Code)

Max Activating Token Index: 519

Text #1

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5043. Min Act: -0.0001

Data Index: 1462079 (Python Code)

Max Activating Token Index: 655

Text #2

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.3032. Min Act: -0.0001

Data Index: 1447028 (Python Code)

Max Activating Token Index: 846

Text #3

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.2463. Min Act: -0.0001

Data Index: 1425054 (Python Code)

Max Activating Token Index: 413

Text #4

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.0219. Min Act: -0.0001

Data Index: 1612907 (Python Code)

Max Activating Token Index: 591

Text #5

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.1003. Min Act: -0.0001

Data Index: 1431076 (Python Code)

Max Activating Token Index: 384

Text #6

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.0550. Min Act: -0.0001

Data Index: 1578833 (Python Code)

Max Activating Token Index: 1005

Text #7

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.0382. Min Act: -0.0001

Data Index: 1450553 (Python Code)

Max Activating Token Index: 711

Text #8

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.8832. Min Act: -0.0001

Data Index: 1365702 (Python Code)

Max Activating Token Index: 286

Text #9

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.8011. Min Act: -0.0001

Data Index: 1626238 (Python Code)

Max Activating Token Index: 499

Text #10

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.0095. Min Act: -0.0001

Data Index: 1569557 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.8392. Min Act: -0.0001

Data Index: 1440692 (Python Code)

Max Activating Token Index: 375

Text #12

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.7532. Min Act: -0.0001

Data Index: 1410648 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.7015. Min Act: -0.0001

Data Index: 1601681 (Python Code)

Max Activating Token Index: 879

Text #14

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.9425. Min Act: -0.0001

Data Index: 1542946 (Python Code)

Max Activating Token Index: 958

Text #15

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.7337. Min Act: -0.0001

Data Index: 1525233 (Python Code)

Max Activating Token Index: 376

Text #16

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.0976. Min Act: -0.0001

Data Index: 1451931 (Python Code)

Max Activating Token Index: 609

Text #17

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.7825. Min Act: -0.0001

Data Index: 1634917 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.7717. Min Act: -0.0001

Data Index: 1578264 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 3.8254. Min Range: -3.8254

Max Act: 2.6270. Min Act: -0.0001

Data Index: 1509785 (Python Code)

Max Activating Token Index: 841