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

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

Neuron 692 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4945. Min Range: -2.4945

Max Act: 2.4945. Min Act: -0.0000

Data Index: 1595560 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 2.4945. Min Range: -2.4945

Max Act: 2.2472. Min Act: -0.0000

Data Index: 1545155 (Python Code)

Max Activating Token Index: 550

Text #2

Max Range: 2.4945. Min Range: -2.4945

Max Act: 2.2080. Min Act: -0.0000

Data Index: 1425021 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 2.4945. Min Range: -2.4945

Max Act: 2.0673. Min Act: -0.0000

Data Index: 1383413 (Python Code)

Max Activating Token Index: 998

Text #4

Max Range: 2.4945. Min Range: -2.4945

Max Act: 2.1354. Min Act: -0.0000

Data Index: 1629429 (Python Code)

Max Activating Token Index: 329

Text #5

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.9795. Min Act: -0.0000

Data Index: 1368782 (Python Code)

Max Activating Token Index: 718

Text #6

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.9436. Min Act: -0.0000

Data Index: 1409145 (Python Code)

Max Activating Token Index: 974

Text #7

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.8239. Min Act: -0.0000

Data Index: 1544074 (Python Code)

Max Activating Token Index: 417

Text #8

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.9108. Min Act: -0.0000

Data Index: 1616900 (Python Code)

Max Activating Token Index: 21

Text #9

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.8028. Min Act: -0.0000

Data Index: 1385049 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 2.4945. Min Range: -2.4945

Max Act: 2.0070. Min Act: -0.0000

Data Index: 1561090 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.8893. Min Act: -0.0000

Data Index: 1542121 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.8865. Min Act: -0.0000

Data Index: 1586235 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.9820. Min Act: -0.0000

Data Index: 1541432 (Python Code)

Max Activating Token Index: 582

Text #14

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.7600. Min Act: -0.0000

Data Index: 1542137 (Python Code)

Max Activating Token Index: 22

Text #15

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1528447 (Python Code)

Max Activating Token Index: 184

Text #16

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.9093. Min Act: -0.0000

Data Index: 1638220 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.8551. Min Act: -0.0000

Data Index: 1397854 (Python Code)

Max Activating Token Index: 885

Text #18

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.8462. Min Act: -0.0000

Data Index: 1540059 (Python Code)

Max Activating Token Index: 713

Text #19

Max Range: 2.4945. Min Range: -2.4945

Max Act: 1.7351. Min Act: -0.0000

Data Index: 1561922 (Python Code)

Max Activating Token Index: 145