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

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

Neuron 817 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: 0.2281. Min Range: -0.2281

Max Act: 0.2281. Min Act: -0.0001

Data Index: 1568707 (Python Code)

Max Activating Token Index: 648

Text #1

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1367934 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1486796 (Python Code)

Max Activating Token Index: 698

Text #3

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1555336 (Python Code)

Max Activating Token Index: 338

Text #4

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1282. Min Act: -0.0000

Data Index: 1640386 (Python Code)

Max Activating Token Index: 58

Text #5

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1444603 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1655193 (Python Code)

Max Activating Token Index: 101

Text #7

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1116. Min Act: -0.0001

Data Index: 13030 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1034. Min Act: -0.0000

Data Index: 271486 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1573396 (Python Code)

Max Activating Token Index: 433

Text #10

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1129. Min Act: -0.0001

Data Index: 64354 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1537547 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.0918. Min Act: -0.0001

Data Index: 881458 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.0972. Min Act: -0.0001

Data Index: 38921 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1423740 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1022. Min Act: -0.0000

Data Index: 935676 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1444747 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.0935. Min Act: -0.0001

Data Index: 276031 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1630993 (Python Code)

Max Activating Token Index: 327

Text #19

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.0923. Min Act: -0.0000

Data Index: 474606 (C4 (Web Text))

Max Activating Token Index: 479