Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4276 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.7694. Min Act: -0.0000

Data Index: 1378350 (Python Code)

Max Activating Token Index: 918

Text #1

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.7119. Min Act: -0.0000

Data Index: 1369859 (Python Code)

Max Activating Token Index: 933

Text #2

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.7177. Min Act: -0.0000

Data Index: 1501510 (Python Code)

Max Activating Token Index: 906

Text #3

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.5472. Min Act: -0.0000

Data Index: 1448591 (Python Code)

Max Activating Token Index: 808

Text #4

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.6137. Min Act: -0.0000

Data Index: 1523964 (Python Code)

Max Activating Token Index: 775

Text #5

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.5452. Min Act: -0.0000

Data Index: 1508258 (Python Code)

Max Activating Token Index: 839

Text #6

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.5335. Min Act: -0.0000

Data Index: 1400745 (Python Code)

Max Activating Token Index: 561

Text #7

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.6201. Min Act: -0.0000

Data Index: 1606129 (Python Code)

Max Activating Token Index: 786

Text #8

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.6898. Min Act: -0.0000

Data Index: 1605341 (Python Code)

Max Activating Token Index: 632

Text #9

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.6960. Min Act: -0.0000

Data Index: 1437070 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.6676. Min Act: -0.0000

Data Index: 1400309 (Python Code)

Max Activating Token Index: 697

Text #11

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.5447. Min Act: -0.0000

Data Index: 1536275 (Python Code)

Max Activating Token Index: 867

Text #12

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.6003. Min Act: -0.0000

Data Index: 1602820 (Python Code)

Max Activating Token Index: 947

Text #13

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1500452 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1618680 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.5113. Min Act: -0.0000

Data Index: 1462419 (Python Code)

Max Activating Token Index: 478

Text #16

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.5050. Min Act: -0.0000

Data Index: 1504250 (Python Code)

Max Activating Token Index: 633

Text #17

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.4826. Min Act: -0.0000

Data Index: 1507654 (Python Code)

Max Activating Token Index: 647

Text #18

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.4014. Min Act: -0.0000

Data Index: 1411554 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.4785. Min Act: -0.0000

Data Index: 1463328 (Python Code)

Max Activating Token Index: 633