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

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

Neuron 2586 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1757. Min Range: -1.1757

Max Act: 1.1757. Min Act: -0.0001

Data Index: 1372777 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9231. Min Act: -0.0001

Data Index: 1493537 (Python Code)

Max Activating Token Index: 325

Text #2

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.7801. Min Act: -0.0001

Data Index: 1619109 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8707. Min Act: -0.0001

Data Index: 1386985 (Python Code)

Max Activating Token Index: 52

Text #4

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8621. Min Act: -0.0001

Data Index: 1626939 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.9018. Min Act: -0.0001

Data Index: 1570243 (Python Code)

Max Activating Token Index: 763

Text #6

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8765. Min Act: -0.0001

Data Index: 1591432 (Python Code)

Max Activating Token Index: 277

Text #7

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.7895. Min Act: -0.0001

Data Index: 1437213 (Python Code)

Max Activating Token Index: 265

Text #8

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.6430. Min Act: -0.0001

Data Index: 1466047 (Python Code)

Max Activating Token Index: 331

Text #9

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8254. Min Act: -0.0001

Data Index: 1461181 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8761. Min Act: -0.0001

Data Index: 1643163 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.7736. Min Act: -0.0001

Data Index: 1465347 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.7637. Min Act: -0.0001

Data Index: 1409597 (Python Code)

Max Activating Token Index: 735

Text #13

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.7343. Min Act: -0.0001

Data Index: 1510379 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8130. Min Act: -0.0001

Data Index: 1518311 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.7876. Min Act: -0.0001

Data Index: 1553960 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8147. Min Act: -0.0001

Data Index: 1500479 (Python Code)

Max Activating Token Index: 265

Text #17

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.8052. Min Act: -0.0001

Data Index: 1601040 (Python Code)

Max Activating Token Index: 477

Text #18

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.7910. Min Act: -0.0001

Data Index: 1627042 (Python Code)

Max Activating Token Index: 995

Text #19

Max Range: 1.1757. Min Range: -1.1757

Max Act: 0.7261. Min Act: -0.0001

Data Index: 1575390 (Python Code)

Max Activating Token Index: 65