Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4380 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.9039. Min Act: -0.0000

Data Index: 649254 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.8936. Min Act: 0.0000

Data Index: 1584436 (Python Code)

Max Activating Token Index: 931

Text #2

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1541295 (Python Code)

Max Activating Token Index: 194

Text #3

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1440491 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.6038. Min Act: 0.0000

Data Index: 1537520 (Python Code)

Max Activating Token Index: 498

Text #5

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1638315 (Python Code)

Max Activating Token Index: 421

Text #6

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.5871. Min Act: 0.0000

Data Index: 1379778 (Python Code)

Max Activating Token Index: 746

Text #7

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1612949 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1557294 (Python Code)

Max Activating Token Index: 497

Text #9

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.6322. Min Act: 0.0000

Data Index: 1508410 (Python Code)

Max Activating Token Index: 510

Text #10

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.6183. Min Act: 0.0000

Data Index: 1645446 (Python Code)

Max Activating Token Index: 139

Text #11

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1452586 (Python Code)

Max Activating Token Index: 920

Text #12

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.5931. Min Act: 0.0000

Data Index: 1426224 (Python Code)

Max Activating Token Index: 767

Text #13

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.6032. Min Act: 0.0002

Data Index: 1428624 (Python Code)

Max Activating Token Index: 119

Text #14

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1423551 (Python Code)

Max Activating Token Index: 494

Text #15

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1537280 (Python Code)

Max Activating Token Index: 598

Text #16

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1597330 (Python Code)

Max Activating Token Index: 318

Text #17

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1437586 (Python Code)

Max Activating Token Index: 726

Text #18

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1504323 (Python Code)

Max Activating Token Index: 816

Text #19

Max Range: 0.9039. Min Range: -0.9039

Max Act: 0.5697. Min Act: 0.0000

Data Index: 1487197 (Python Code)

Max Activating Token Index: 213