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

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

Neuron 2717 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2215. Min Range: -3.2215

Max Act: 3.2215. Min Act: 0.0000

Data Index: 1380628 (Python Code)

Max Activating Token Index: 616

Text #1

Max Range: 3.2215. Min Range: -3.2215

Max Act: 3.1954. Min Act: -0.0000

Data Index: 1639775 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.7678. Min Act: 0.0000

Data Index: 1441791 (Python Code)

Max Activating Token Index: 129

Text #3

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.7483. Min Act: 0.0000

Data Index: 1645968 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.5702. Min Act: -0.0000

Data Index: 1479560 (Python Code)

Max Activating Token Index: 954

Text #5

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.5610. Min Act: 0.0001

Data Index: 1645183 (Python Code)

Max Activating Token Index: 107

Text #6

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.6821. Min Act: 0.0000

Data Index: 1445769 (Python Code)

Max Activating Token Index: 138

Text #7

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.6700. Min Act: 0.0001

Data Index: 1553690 (Python Code)

Max Activating Token Index: 145

Text #8

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.6691. Min Act: 0.0001

Data Index: 1447558 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.7840. Min Act: -0.0000

Data Index: 1476378 (Python Code)

Max Activating Token Index: 1017

Text #10

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.6446. Min Act: -0.0000

Data Index: 1374298 (Python Code)

Max Activating Token Index: 93

Text #11

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.6534. Min Act: 0.0000

Data Index: 1627010 (Python Code)

Max Activating Token Index: 737

Text #12

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.6411. Min Act: -0.0000

Data Index: 1615979 (Python Code)

Max Activating Token Index: 655

Text #13

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.7505. Min Act: -0.0000

Data Index: 1572797 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.5011. Min Act: -0.0000

Data Index: 1458955 (Python Code)

Max Activating Token Index: 508

Text #15

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.6104. Min Act: -0.0000

Data Index: 1455370 (Python Code)

Max Activating Token Index: 517

Text #16

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.4680. Min Act: 0.0000

Data Index: 1426971 (Python Code)

Max Activating Token Index: 823

Text #17

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.5818. Min Act: 0.0000

Data Index: 1374857 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.5892. Min Act: 0.0000

Data Index: 1651964 (Python Code)

Max Activating Token Index: 82

Text #19

Max Range: 3.2215. Min Range: -3.2215

Max Act: 2.5698. Min Act: 0.0000

Data Index: 1389692 (Python Code)

Max Activating Token Index: 576