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

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

Neuron 2244 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4931. Min Range: -7.4931

Max Act: 7.4931. Min Act: -0.0000

Data Index: 1644900 (Python Code)

Max Activating Token Index: 928

Text #1

Max Range: 7.4931. Min Range: -7.4931

Max Act: 6.1777. Min Act: -0.0000

Data Index: 1410541 (Python Code)

Max Activating Token Index: 340

Text #2

Max Range: 7.4931. Min Range: -7.4931

Max Act: 6.0724. Min Act: -0.0000

Data Index: 1377593 (Python Code)

Max Activating Token Index: 811

Text #3

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.6462. Min Act: -0.0000

Data Index: 1457817 (Python Code)

Max Activating Token Index: 947

Text #4

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.3442. Min Act: -0.0000

Data Index: 1442789 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.4902. Min Act: -0.0000

Data Index: 1459863 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.4360. Min Act: -0.0000

Data Index: 50547 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.0640. Min Act: -0.0000

Data Index: 1517300 (Python Code)

Max Activating Token Index: 829

Text #8

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.4177. Min Act: -0.0000

Data Index: 1402868 (Python Code)

Max Activating Token Index: 966

Text #9

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.0218. Min Act: -0.0000

Data Index: 1585701 (Python Code)

Max Activating Token Index: 663

Text #10

Max Range: 7.4931. Min Range: -7.4931

Max Act: 4.9830. Min Act: -0.0000

Data Index: 1568951 (Python Code)

Max Activating Token Index: 271

Text #11

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.0921. Min Act: -0.0000

Data Index: 1549376 (Python Code)

Max Activating Token Index: 211

Text #12

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.0744. Min Act: -0.0000

Data Index: 1600071 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.2593. Min Act: -0.0000

Data Index: 1277365 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 7.4931. Min Range: -7.4931

Max Act: 4.8825. Min Act: -0.0000

Data Index: 1537597 (Python Code)

Max Activating Token Index: 895

Text #15

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.0622. Min Act: -0.0000

Data Index: 1474934 (Python Code)

Max Activating Token Index: 594

Text #16

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.0215. Min Act: -0.0000

Data Index: 1525014 (Python Code)

Max Activating Token Index: 34

Text #17

Max Range: 7.4931. Min Range: -7.4931

Max Act: 5.2009. Min Act: -0.0000

Data Index: 1413707 (Python Code)

Max Activating Token Index: 443

Text #18

Max Range: 7.4931. Min Range: -7.4931

Max Act: 4.5907. Min Act: -0.0000

Data Index: 1455686 (Python Code)

Max Activating Token Index: 828

Text #19

Max Range: 7.4931. Min Range: -7.4931

Max Act: 4.9183. Min Act: -0.0000

Data Index: 1617855 (Python Code)

Max Activating Token Index: 277