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

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

Neuron 4565 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: 1.6634. Min Range: -1.6634

Max Act: 1.6634. Min Act: -0.0000

Data Index: 45657 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.4270. Min Act: -0.0000

Data Index: 1242631 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.4804. Min Act: -0.0000

Data Index: 932780 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3936. Min Act: -0.0000

Data Index: 408062 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.4115. Min Act: -0.0000

Data Index: 962691 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.4107. Min Act: -0.0000

Data Index: 655286 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.2582. Min Act: -0.0000

Data Index: 552726 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.4218. Min Act: -0.0000

Data Index: 338432 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3215. Min Act: -0.0000

Data Index: 391653 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1234668 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3594. Min Act: -0.0000

Data Index: 629044 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.2742. Min Act: -0.0000

Data Index: 118469 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.2810. Min Act: -0.0000

Data Index: 1317271 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.2483. Min Act: -0.0000

Data Index: 311612 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.2407. Min Act: -0.0000

Data Index: 709098 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.3160. Min Act: -0.0000

Data Index: 1344953 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.1631. Min Act: -0.0000

Data Index: 354501 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.2252. Min Act: -0.0000

Data Index: 797158 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.2218. Min Act: -0.0000

Data Index: 414986 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 1.6634. Min Range: -1.6634

Max Act: 1.1849. Min Act: -0.0000

Data Index: 426656 (C4 (Web Text))

Max Activating Token Index: 855