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

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

Neuron 3195 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.3018. Min Act: -0.0001

Data Index: 1552099 (Python Code)

Max Activating Token Index: 495

Text #1

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.2933. Min Act: -0.0001

Data Index: 1632701 (Python Code)

Max Activating Token Index: 660

Text #2

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.2866. Min Act: -0.0001

Data Index: 1549912 (Python Code)

Max Activating Token Index: 256

Text #3

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.2403. Min Act: -0.0001

Data Index: 1398758 (Python Code)

Max Activating Token Index: 798

Text #4

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.3802. Min Act: -0.0001

Data Index: 1381725 (Python Code)

Max Activating Token Index: 545

Text #5

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.2939. Min Act: -0.0001

Data Index: 1539555 (Python Code)

Max Activating Token Index: 521

Text #6

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.1834. Min Act: -0.0001

Data Index: 1494198 (Python Code)

Max Activating Token Index: 421

Text #7

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.2418. Min Act: -0.0001

Data Index: 1426018 (Python Code)

Max Activating Token Index: 102

Text #8

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.2722. Min Act: -0.0001

Data Index: 1617482 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.1581. Min Act: -0.0001

Data Index: 1552643 (Python Code)

Max Activating Token Index: 327

Text #10

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.1867. Min Act: -0.0001

Data Index: 1607090 (Python Code)

Max Activating Token Index: 419

Text #11

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.1188. Min Act: -0.0001

Data Index: 1441729 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.1144. Min Act: -0.0001

Data Index: 1445392 (Python Code)

Max Activating Token Index: 509

Text #13

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.1083. Min Act: -0.0001

Data Index: 1632291 (Python Code)

Max Activating Token Index: 779

Text #14

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.2203. Min Act: -0.0001

Data Index: 1572071 (Python Code)

Max Activating Token Index: 474

Text #15

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0632. Min Act: -0.0001

Data Index: 1461393 (Python Code)

Max Activating Token Index: 570

Text #16

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0854. Min Act: -0.0001

Data Index: 1453052 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0921. Min Act: -0.0001

Data Index: 1557850 (Python Code)

Max Activating Token Index: 228

Text #18

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0449. Min Act: -0.0001

Data Index: 1606922 (Python Code)

Max Activating Token Index: 844

Text #19

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0020. Min Act: -0.0001

Data Index: 1407965 (Python Code)

Max Activating Token Index: 223