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

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

Neuron 4821 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9151. Min Range: -4.9151

Max Act: 4.9151. Min Act: -0.0000

Data Index: 1482829 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 4.9151. Min Range: -4.9151

Max Act: 4.6614. Min Act: -0.0000

Data Index: 1459420 (Python Code)

Max Activating Token Index: 56

Text #2

Max Range: 4.9151. Min Range: -4.9151

Max Act: 4.5600. Min Act: -0.0000

Data Index: 1481162 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 4.9151. Min Range: -4.9151

Max Act: 4.4492. Min Act: -0.0000

Data Index: 1638737 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 4.9151. Min Range: -4.9151

Max Act: 4.2305. Min Act: -0.0000

Data Index: 1555949 (Python Code)

Max Activating Token Index: 47

Text #5

Max Range: 4.9151. Min Range: -4.9151

Max Act: 4.2988. Min Act: -0.0000

Data Index: 1493681 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 4.9151. Min Range: -4.9151

Max Act: 3.8183. Min Act: -0.0000

Data Index: 1612230 (Python Code)

Max Activating Token Index: 446

Text #7

Max Range: 4.9151. Min Range: -4.9151

Max Act: 3.4717. Min Act: -0.0000

Data Index: 1600572 (Python Code)

Max Activating Token Index: 797

Text #8

Max Range: 4.9151. Min Range: -4.9151

Max Act: 3.8108. Min Act: -0.0000

Data Index: 1565159 (Python Code)

Max Activating Token Index: 204

Text #9

Max Range: 4.9151. Min Range: -4.9151

Max Act: 4.0809. Min Act: -0.0000

Data Index: 1593511 (Python Code)

Max Activating Token Index: 291

Text #10

Max Range: 4.9151. Min Range: -4.9151

Max Act: 3.8911. Min Act: -0.0000

Data Index: 1475412 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 4.9151. Min Range: -4.9151

Max Act: 4.0556. Min Act: -0.0000

Data Index: 1366938 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 4.9151. Min Range: -4.9151

Max Act: 3.7964. Min Act: -0.0000

Data Index: 1620190 (Python Code)

Max Activating Token Index: 264

Text #13

Max Range: 4.9151. Min Range: -4.9151

Max Act: 3.8078. Min Act: -0.0000

Data Index: 1385878 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 4.9151. Min Range: -4.9151

Max Act: 3.9586. Min Act: -0.0000

Data Index: 1394408 (Python Code)

Max Activating Token Index: 132

Text #15

Max Range: 4.9151. Min Range: -4.9151

Max Act: 4.1355. Min Act: -0.0000

Data Index: 1548516 (Python Code)

Max Activating Token Index: 320

Text #16

Max Range: 4.9151. Min Range: -4.9151

Max Act: 3.9415. Min Act: -0.0000

Data Index: 1479088 (Python Code)

Max Activating Token Index: 80

Text #17

Max Range: 4.9151. Min Range: -4.9151

Max Act: 3.6702. Min Act: -0.0000

Data Index: 1375317 (Python Code)

Max Activating Token Index: 196

Text #18

Max Range: 4.9151. Min Range: -4.9151

Max Act: 3.9596. Min Act: -0.0000

Data Index: 1586808 (Python Code)

Max Activating Token Index: 479

Text #19

Max Range: 4.9151. Min Range: -4.9151

Max Act: 3.6455. Min Act: -0.0000

Data Index: 1409560 (Python Code)

Max Activating Token Index: 804