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

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

Neuron 4394 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.5846. Min Act: -0.0000

Data Index: 1345818 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.2546. Min Act: -0.0000

Data Index: 563320 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.4241. Min Act: -0.0000

Data Index: 492933 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.2164. Min Act: -0.0000

Data Index: 734943 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1233685 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.2389. Min Act: -0.0000

Data Index: 785227 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.2512. Min Act: -0.0000

Data Index: 1515446 (Python Code)

Max Activating Token Index: 577

Text #7

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.1790. Min Act: -0.0000

Data Index: 1319354 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.1096. Min Act: -0.0000

Data Index: 293133 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.1777. Min Act: -0.0000

Data Index: 642369 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0800. Min Act: -0.0000

Data Index: 951336 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1558694 (Python Code)

Max Activating Token Index: 54

Text #12

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0727. Min Act: -0.0000

Data Index: 931280 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0105. Min Act: -0.0000

Data Index: 896337 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1338984 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0439. Min Act: -0.0000

Data Index: 880263 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 1.5846. Min Range: -1.5846

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1347775 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 1.5846. Min Range: -1.5846

Max Act: 0.8914. Min Act: -0.0000

Data Index: 194616 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 1.5846. Min Range: -1.5846

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1206528 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 1.5846. Min Range: -1.5846

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1229802 (C4 (Web Text))

Max Activating Token Index: 46