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

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

Neuron 1759 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4769. Min Range: -3.4769

Max Act: 3.4769. Min Act: -0.0000

Data Index: 1600922 (Python Code)

Max Activating Token Index: 518

Text #1

Max Range: 3.4769. Min Range: -3.4769

Max Act: 3.3286. Min Act: -0.0000

Data Index: 1501492 (Python Code)

Max Activating Token Index: 206

Text #2

Max Range: 3.4769. Min Range: -3.4769

Max Act: 3.3589. Min Act: -0.0000

Data Index: 1398585 (Python Code)

Max Activating Token Index: 469

Text #3

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.9908. Min Act: -0.0000

Data Index: 1399218 (Python Code)

Max Activating Token Index: 688

Text #4

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.7896. Min Act: -0.0000

Data Index: 1436600 (Python Code)

Max Activating Token Index: 699

Text #5

Max Range: 3.4769. Min Range: -3.4769

Max Act: 3.0541. Min Act: -0.0000

Data Index: 1498216 (Python Code)

Max Activating Token Index: 258

Text #6

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.9002. Min Act: -0.0000

Data Index: 1590892 (Python Code)

Max Activating Token Index: 605

Text #7

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.8850. Min Act: -0.0000

Data Index: 1578978 (Python Code)

Max Activating Token Index: 660

Text #8

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.7019. Min Act: -0.0000

Data Index: 1397265 (Python Code)

Max Activating Token Index: 727

Text #9

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.7280. Min Act: -0.0000

Data Index: 1458196 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.4286. Min Act: -0.0000

Data Index: 561960 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.6899. Min Act: -0.0000

Data Index: 1638481 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.6889. Min Act: -0.0000

Data Index: 1648780 (Python Code)

Max Activating Token Index: 502

Text #13

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.6544. Min Act: -0.0000

Data Index: 1473084 (Python Code)

Max Activating Token Index: 536

Text #14

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.6473. Min Act: -0.0000

Data Index: 1645678 (Python Code)

Max Activating Token Index: 378

Text #15

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.5816. Min Act: -0.0000

Data Index: 1576592 (Python Code)

Max Activating Token Index: 683

Text #16

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.5963. Min Act: -0.0000

Data Index: 1626309 (Python Code)

Max Activating Token Index: 293

Text #17

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.6039. Min Act: -0.0000

Data Index: 795521 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.4273. Min Act: -0.0000

Data Index: 1576231 (Python Code)

Max Activating Token Index: 479

Text #19

Max Range: 3.4769. Min Range: -3.4769

Max Act: 2.5448. Min Act: -0.0000

Data Index: 1517234 (Python Code)

Max Activating Token Index: 1001