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

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

Neuron 3692 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2936. Min Act: -0.0001

Data Index: 1119699 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1654955 (Python Code)

Max Activating Token Index: 336

Text #2

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2228. Min Act: -0.0001

Data Index: 639052 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1455630 (Python Code)

Max Activating Token Index: 262

Text #4

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1548071 (Python Code)

Max Activating Token Index: 204

Text #5

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1447469 (Python Code)

Max Activating Token Index: 535

Text #6

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1415263 (Python Code)

Max Activating Token Index: 419

Text #7

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1638409 (Python Code)

Max Activating Token Index: 977

Text #8

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1352064 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1569984 (Python Code)

Max Activating Token Index: 346

Text #10

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1489975 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1591157 (Python Code)

Max Activating Token Index: 845

Text #12

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1893. Min Act: -0.0001

Data Index: 1636475 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1534915 (Python Code)

Max Activating Token Index: 867

Text #14

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1564785 (Python Code)

Max Activating Token Index: 464

Text #15

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1641089 (Python Code)

Max Activating Token Index: 73

Text #16

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1583146 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1432164 (Python Code)

Max Activating Token Index: 214

Text #18

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1405291 (Python Code)

Max Activating Token Index: 51

Text #19

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1392580 (Python Code)

Max Activating Token Index: 697