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

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

Neuron 3534 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: 1.5099. Min Range: -1.5099

Max Act: 1.5099. Min Act: -0.0001

Data Index: 1456578 (Python Code)

Max Activating Token Index: 699

Text #1

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.4766. Min Act: -0.0001

Data Index: 1542523 (Python Code)

Max Activating Token Index: 777

Text #2

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.4289. Min Act: -0.0001

Data Index: 1638993 (Python Code)

Max Activating Token Index: 702

Text #3

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.3721. Min Act: -0.0001

Data Index: 1470776 (Python Code)

Max Activating Token Index: 842

Text #4

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.3556. Min Act: -0.0001

Data Index: 1646570 (Python Code)

Max Activating Token Index: 514

Text #5

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.3553. Min Act: -0.0001

Data Index: 1489980 (Python Code)

Max Activating Token Index: 173

Text #6

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.3171. Min Act: -0.0001

Data Index: 1498874 (Python Code)

Max Activating Token Index: 262

Text #7

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.2133. Min Act: -0.0001

Data Index: 1584935 (Python Code)

Max Activating Token Index: 439

Text #8

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.2329. Min Act: -0.0001

Data Index: 1386859 (Python Code)

Max Activating Token Index: 346

Text #9

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.1879. Min Act: -0.0001

Data Index: 1493015 (Python Code)

Max Activating Token Index: 228

Text #10

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.1461. Min Act: -0.0001

Data Index: 1616548 (Python Code)

Max Activating Token Index: 902

Text #11

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.1154. Min Act: -0.0001

Data Index: 1427490 (Python Code)

Max Activating Token Index: 356

Text #12

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.1043. Min Act: -0.0001

Data Index: 1656739 (Python Code)

Max Activating Token Index: 939

Text #13

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.1453. Min Act: -0.0001

Data Index: 1485339 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.0334. Min Act: -0.0001

Data Index: 1606110 (Python Code)

Max Activating Token Index: 509

Text #15

Max Range: 1.5099. Min Range: -1.5099

Max Act: 0.9667. Min Act: -0.0001

Data Index: 1543847 (Python Code)

Max Activating Token Index: 999

Text #16

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.0636. Min Act: -0.0001

Data Index: 1412876 (Python Code)

Max Activating Token Index: 634

Text #17

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.0214. Min Act: -0.0001

Data Index: 1640061 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 1.5099. Min Range: -1.5099

Max Act: 1.0613. Min Act: -0.0001

Data Index: 1545405 (Python Code)

Max Activating Token Index: 293

Text #19

Max Range: 1.5099. Min Range: -1.5099

Max Act: 0.9922. Min Act: -0.0001

Data Index: 1479354 (Python Code)

Max Activating Token Index: 18