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

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

Neuron 5453 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.2981. Min Act: -0.0000

Data Index: 1360863 (Python Code)

Max Activating Token Index: 896

Text #1

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.1142. Min Act: -0.0000

Data Index: 1630642 (Python Code)

Max Activating Token Index: 990

Text #2

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.0804. Min Act: -0.0000

Data Index: 1445027 (Python Code)

Max Activating Token Index: 856

Text #3

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.0596. Min Act: -0.0000

Data Index: 1499956 (Python Code)

Max Activating Token Index: 888

Text #4

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.0557. Min Act: -0.0000

Data Index: 1479979 (Python Code)

Max Activating Token Index: 805

Text #5

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.2048. Min Act: -0.0000

Data Index: 1633081 (Python Code)

Max Activating Token Index: 856

Text #6

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.1024. Min Act: -0.0000

Data Index: 1435709 (Python Code)

Max Activating Token Index: 820

Text #7

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.2565. Min Act: -0.0000

Data Index: 1546696 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 4.2981. Min Range: -4.2981

Max Act: 3.9210. Min Act: -0.0000

Data Index: 1391217 (Python Code)

Max Activating Token Index: 920

Text #9

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.0624. Min Act: -0.0000

Data Index: 1476632 (Python Code)

Max Activating Token Index: 827

Text #10

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.0655. Min Act: -0.0000

Data Index: 1517421 (Python Code)

Max Activating Token Index: 902

Text #11

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.0466. Min Act: -0.0000

Data Index: 1454497 (Python Code)

Max Activating Token Index: 856

Text #12

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.0437. Min Act: -0.0000

Data Index: 1387529 (Python Code)

Max Activating Token Index: 845

Text #13

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.0154. Min Act: -0.0000

Data Index: 1533455 (Python Code)

Max Activating Token Index: 814

Text #14

Max Range: 4.2981. Min Range: -4.2981

Max Act: 4.0825. Min Act: -0.0000

Data Index: 1474663 (Python Code)

Max Activating Token Index: 864

Text #15

Max Range: 4.2981. Min Range: -4.2981

Max Act: 3.9386. Min Act: -0.0000

Data Index: 1476582 (Python Code)

Max Activating Token Index: 1018

Text #16

Max Range: 4.2981. Min Range: -4.2981

Max Act: 3.9348. Min Act: -0.0000

Data Index: 1644951 (Python Code)

Max Activating Token Index: 977

Text #17

Max Range: 4.2981. Min Range: -4.2981

Max Act: 3.9550. Min Act: -0.0000

Data Index: 1399412 (Python Code)

Max Activating Token Index: 871

Text #18

Max Range: 4.2981. Min Range: -4.2981

Max Act: 3.9501. Min Act: -0.0000

Data Index: 1646012 (Python Code)

Max Activating Token Index: 784

Text #19

Max Range: 4.2981. Min Range: -4.2981

Max Act: 3.9199. Min Act: -0.0000

Data Index: 1543426 (Python Code)

Max Activating Token Index: 597