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

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

Neuron 3178 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.8799. Min Act: -0.0000

Data Index: 600266 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.7302. Min Act: 0.0000

Data Index: 1052916 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.4622. Min Act: -0.0000

Data Index: 806535 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.4265. Min Act: -0.0000

Data Index: 212868 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.2457. Min Act: -0.0000

Data Index: 686961 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.1686. Min Act: -0.0000

Data Index: 1133420 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1241117 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.2070. Min Act: -0.0000

Data Index: 224939 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.0360. Min Act: -0.0000

Data Index: 351317 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.0415. Min Act: -0.0000

Data Index: 273716 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.0267. Min Act: -0.0000

Data Index: 507504 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.0201. Min Act: -0.0000

Data Index: 741436 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1595908 (Python Code)

Max Activating Token Index: 400

Text #13

Max Range: 1.8799. Min Range: -1.8799

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1281299 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.0532. Min Act: -0.0000

Data Index: 1174232 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.0482. Min Act: -0.0000

Data Index: 449814 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 1.8799. Min Range: -1.8799

Max Act: 1.0524. Min Act: 0.0000

Data Index: 1302742 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 1.8799. Min Range: -1.8799

Max Act: 0.8928. Min Act: -0.0000

Data Index: 133705 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 1.8799. Min Range: -1.8799

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1006205 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.8799. Min Range: -1.8799

Max Act: 0.8416. Min Act: -0.0000

Data Index: 790284 (C4 (Web Text))

Max Activating Token Index: 563