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

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

Neuron 1997 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.7477. Min Act: -0.0001

Data Index: 1494942 (Python Code)

Max Activating Token Index: 913

Text #1

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.6629. Min Act: -0.0001

Data Index: 1384673 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.5519. Min Act: -0.0001

Data Index: 1460834 (Python Code)

Max Activating Token Index: 130

Text #3

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.3063. Min Act: -0.0001

Data Index: 1537656 (Python Code)

Max Activating Token Index: 1020

Text #4

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.2471. Min Act: -0.0001

Data Index: 1526402 (Python Code)

Max Activating Token Index: 664

Text #5

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.1097. Min Act: -0.0001

Data Index: 1561447 (Python Code)

Max Activating Token Index: 963

Text #6

Max Range: 3.7477. Min Range: -3.7477

Max Act: 2.9030. Min Act: -0.0001

Data Index: 1507670 (Python Code)

Max Activating Token Index: 849

Text #7

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.2281. Min Act: -0.0001

Data Index: 1384133 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.1665. Min Act: -0.0001

Data Index: 1404068 (Python Code)

Max Activating Token Index: 185

Text #9

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.1536. Min Act: -0.0001

Data Index: 1478107 (Python Code)

Max Activating Token Index: 1016

Text #10

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.2987. Min Act: -0.0001

Data Index: 762293 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 3.7477. Min Range: -3.7477

Max Act: 2.9779. Min Act: -0.0001

Data Index: 1538565 (Python Code)

Max Activating Token Index: 856

Text #12

Max Range: 3.7477. Min Range: -3.7477

Max Act: 2.9874. Min Act: -0.0001

Data Index: 1374320 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.0760. Min Act: -0.0001

Data Index: 1362467 (Python Code)

Max Activating Token Index: 586

Text #14

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.0206. Min Act: -0.0001

Data Index: 1401589 (Python Code)

Max Activating Token Index: 912

Text #15

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.1657. Min Act: -0.0001

Data Index: 1624153 (Python Code)

Max Activating Token Index: 872

Text #16

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.0509. Min Act: -0.0001

Data Index: 1373818 (Python Code)

Max Activating Token Index: 666

Text #17

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.4893. Min Act: -0.0001

Data Index: 1544832 (Python Code)

Max Activating Token Index: 910

Text #18

Max Range: 3.7477. Min Range: -3.7477

Max Act: 2.8980. Min Act: -0.0001

Data Index: 1598975 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 3.7477. Min Range: -3.7477

Max Act: 3.0347. Min Act: -0.0001

Data Index: 1411571 (Python Code)

Max Activating Token Index: 555