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

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

Neuron 675 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: 0.8401. Min Range: -0.8401

Max Act: 0.8401. Min Act: -0.0001

Data Index: 1220163 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1508788 (Python Code)

Max Activating Token Index: 143

Text #2

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6649. Min Act: -0.0000

Data Index: 90178 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6894. Min Act: -0.0000

Data Index: 564433 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1610795 (Python Code)

Max Activating Token Index: 143

Text #5

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6837. Min Act: -0.0001

Data Index: 1423333 (Python Code)

Max Activating Token Index: 873

Text #6

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6188. Min Act: -0.0001

Data Index: 94511 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6767. Min Act: -0.0001

Data Index: 178473 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.7183. Min Act: -0.0001

Data Index: 1598932 (Python Code)

Max Activating Token Index: 278

Text #9

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1586132 (Python Code)

Max Activating Token Index: 298

Text #10

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1405987 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1598029 (Python Code)

Max Activating Token Index: 878

Text #12

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6754. Min Act: -0.0001

Data Index: 1499101 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5951. Min Act: -0.0000

Data Index: 245129 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1541442 (Python Code)

Max Activating Token Index: 229

Text #15

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.7330. Min Act: -0.0000

Data Index: 634081 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1407686 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6265. Min Act: -0.0001

Data Index: 323214 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1615716 (Python Code)

Max Activating Token Index: 1021

Text #19

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6103. Min Act: -0.0001

Data Index: 1508559 (Python Code)

Max Activating Token Index: 873