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

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

Neuron 2965 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5215. Min Range: -2.5215

Max Act: 2.5215. Min Act: -0.0000

Data Index: 943190 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 2.5215. Min Range: -2.5215

Max Act: 2.2242. Min Act: -0.0000

Data Index: 292192 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.9588. Min Act: -0.0000

Data Index: 389765 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.7591. Min Act: -0.0000

Data Index: 68475 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.7462. Min Act: 0.0000

Data Index: 331690 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.7560. Min Act: 0.0000

Data Index: 277560 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.7441. Min Act: -0.0000

Data Index: 773498 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.7453. Min Act: -0.0000

Data Index: 610254 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.6699. Min Act: -0.0000

Data Index: 837594 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.7685. Min Act: -0.0000

Data Index: 1187611 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.6554. Min Act: 0.0000

Data Index: 108824 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.6572. Min Act: -0.0000

Data Index: 1273532 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.6472. Min Act: 0.0001

Data Index: 1172197 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.6016. Min Act: -0.0000

Data Index: 86573 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.4261. Min Act: -0.0000

Data Index: 672238 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.5930. Min Act: -0.0000

Data Index: 752530 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.5848. Min Act: -0.0000

Data Index: 110981 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.5909. Min Act: -0.0000

Data Index: 1437203 (Python Code)

Max Activating Token Index: 547

Text #18

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.5766. Min Act: -0.0000

Data Index: 1167838 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 2.5215. Min Range: -2.5215

Max Act: 1.6777. Min Act: -0.0000

Data Index: 891973 (C4 (Web Text))

Max Activating Token Index: 402