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

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

Neuron 470 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5231. Min Range: -1.5231

Max Act: 1.5231. Min Act: 0.0000

Data Index: 1552042 (Python Code)

Max Activating Token Index: 923

Text #1

Max Range: 1.5231. Min Range: -1.5231

Max Act: 1.2080. Min Act: -0.0000

Data Index: 1409787 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 1.5231. Min Range: -1.5231

Max Act: 1.0756. Min Act: 0.0000

Data Index: 1517462 (Python Code)

Max Activating Token Index: 838

Text #3

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.9239. Min Act: 0.0001

Data Index: 1449724 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 1.5231. Min Range: -1.5231

Max Act: 1.0059. Min Act: 0.0001

Data Index: 1459463 (Python Code)

Max Activating Token Index: 655

Text #5

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.6909. Min Act: -0.0000

Data Index: 1489105 (Python Code)

Max Activating Token Index: 359

Text #6

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.9231. Min Act: 0.0000

Data Index: 1389948 (Python Code)

Max Activating Token Index: 1001

Text #7

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1646780 (Python Code)

Max Activating Token Index: 525

Text #8

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1467782 (Python Code)

Max Activating Token Index: 206

Text #9

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.9157. Min Act: 0.0001

Data Index: 1589888 (Python Code)

Max Activating Token Index: 983

Text #10

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1390159 (Python Code)

Max Activating Token Index: 703

Text #11

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1611984 (Python Code)

Max Activating Token Index: 433

Text #12

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.8392. Min Act: 0.0000

Data Index: 1416874 (Python Code)

Max Activating Token Index: 90

Text #13

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.7882. Min Act: 0.0001

Data Index: 1575467 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.7594. Min Act: 0.0000

Data Index: 1398871 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.8322. Min Act: 0.0001

Data Index: 1628825 (Python Code)

Max Activating Token Index: 359

Text #16

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.7603. Min Act: 0.0001

Data Index: 1389228 (Python Code)

Max Activating Token Index: 762

Text #17

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.7553. Min Act: 0.0000

Data Index: 1636995 (Python Code)

Max Activating Token Index: 427

Text #18

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.8242. Min Act: 0.0000

Data Index: 1640879 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 1.5231. Min Range: -1.5231

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1400444 (Python Code)

Max Activating Token Index: 652