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

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

Neuron 3246 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.7533. Min Act: -0.0001

Data Index: 1377229 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6733. Min Act: -0.0001

Data Index: 1582377 (Python Code)

Max Activating Token Index: 527

Text #2

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6720. Min Act: -0.0001

Data Index: 1562369 (Python Code)

Max Activating Token Index: 137

Text #3

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6765. Min Act: -0.0001

Data Index: 1612606 (Python Code)

Max Activating Token Index: 106

Text #4

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6702. Min Act: -0.0001

Data Index: 1497230 (Python Code)

Max Activating Token Index: 981

Text #5

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6526. Min Act: -0.0001

Data Index: 1422825 (Python Code)

Max Activating Token Index: 268

Text #6

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6522. Min Act: -0.0001

Data Index: 1641795 (Python Code)

Max Activating Token Index: 490

Text #7

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6346. Min Act: -0.0001

Data Index: 1494029 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6519. Min Act: -0.0001

Data Index: 1531126 (Python Code)

Max Activating Token Index: 202

Text #9

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6322. Min Act: -0.0001

Data Index: 1490425 (Python Code)

Max Activating Token Index: 196

Text #10

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6221. Min Act: -0.0001

Data Index: 1379778 (Python Code)

Max Activating Token Index: 91

Text #11

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6304. Min Act: -0.0001

Data Index: 1446967 (Python Code)

Max Activating Token Index: 202

Text #12

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6378. Min Act: -0.0001

Data Index: 1394672 (Python Code)

Max Activating Token Index: 52

Text #13

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6178. Min Act: -0.0001

Data Index: 1504631 (Python Code)

Max Activating Token Index: 568

Text #14

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6304. Min Act: -0.0001

Data Index: 1548052 (Python Code)

Max Activating Token Index: 387

Text #15

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6236. Min Act: -0.0001

Data Index: 1619573 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6044. Min Act: -0.0001

Data Index: 1424650 (Python Code)

Max Activating Token Index: 893

Text #17

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6087. Min Act: -0.0001

Data Index: 1546902 (Python Code)

Max Activating Token Index: 66

Text #18

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.5978. Min Act: -0.0001

Data Index: 1420380 (Python Code)

Max Activating Token Index: 58

Text #19

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.5990. Min Act: -0.0001

Data Index: 1381510 (Python Code)

Max Activating Token Index: 98