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

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

Neuron 2637 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: 3.4932. Min Range: -3.4932

Max Act: 3.4932. Min Act: -0.0000

Data Index: 1530298 (Python Code)

Max Activating Token Index: 520

Text #1

Max Range: 3.4932. Min Range: -3.4932

Max Act: 3.2675. Min Act: -0.0000

Data Index: 1496603 (Python Code)

Max Activating Token Index: 903

Text #2

Max Range: 3.4932. Min Range: -3.4932

Max Act: 3.1300. Min Act: -0.0000

Data Index: 1381941 (Python Code)

Max Activating Token Index: 806

Text #3

Max Range: 3.4932. Min Range: -3.4932

Max Act: 3.0585. Min Act: -0.0000

Data Index: 1588381 (Python Code)

Max Activating Token Index: 919

Text #4

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.8926. Min Act: -0.0000

Data Index: 1378850 (Python Code)

Max Activating Token Index: 742

Text #5

Max Range: 3.4932. Min Range: -3.4932

Max Act: 3.0392. Min Act: -0.0000

Data Index: 1424353 (Python Code)

Max Activating Token Index: 715

Text #6

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.7144. Min Act: -0.0000

Data Index: 1500338 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.8137. Min Act: -0.0000

Data Index: 1598052 (Python Code)

Max Activating Token Index: 578

Text #8

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.6214. Min Act: -0.0000

Data Index: 1532118 (Python Code)

Max Activating Token Index: 698

Text #9

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.8505. Min Act: -0.0000

Data Index: 1388100 (Python Code)

Max Activating Token Index: 542

Text #10

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.6353. Min Act: -0.0000

Data Index: 1514708 (Python Code)

Max Activating Token Index: 497

Text #11

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.3713. Min Act: -0.0000

Data Index: 1418018 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.7867. Min Act: -0.0000

Data Index: 1453862 (Python Code)

Max Activating Token Index: 991

Text #13

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.7216. Min Act: -0.0000

Data Index: 1423960 (Python Code)

Max Activating Token Index: 943

Text #14

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.5752. Min Act: -0.0000

Data Index: 1636444 (Python Code)

Max Activating Token Index: 76

Text #15

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.5312. Min Act: -0.0000

Data Index: 1388075 (Python Code)

Max Activating Token Index: 921

Text #16

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.3213. Min Act: -0.0000

Data Index: 1585992 (Python Code)

Max Activating Token Index: 892

Text #17

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.5110. Min Act: -0.0000

Data Index: 1526807 (Python Code)

Max Activating Token Index: 881

Text #18

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.2335. Min Act: -0.0000

Data Index: 1394402 (Python Code)

Max Activating Token Index: 678

Text #19

Max Range: 3.4932. Min Range: -3.4932

Max Act: 2.3192. Min Act: -0.0000

Data Index: 1418148 (Python Code)

Max Activating Token Index: 731