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

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

Neuron 1877 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: 1.6501. Min Range: -1.6501

Max Act: 1.6501. Min Act: -0.0000

Data Index: 296203 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.6220. Min Act: -0.0000

Data Index: 488816 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.6078. Min Act: -0.0000

Data Index: 710832 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5365. Min Act: -0.0000

Data Index: 842664 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.4217. Min Act: -0.0000

Data Index: 1401048 (Python Code)

Max Activating Token Index: 924

Text #5

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.4313. Min Act: -0.0000

Data Index: 932339 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.3882. Min Act: -0.0000

Data Index: 652236 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.4707. Min Act: -0.0000

Data Index: 1262591 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.4215. Min Act: -0.0000

Data Index: 762274 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.3846. Min Act: -0.0000

Data Index: 226052 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.2328. Min Act: -0.0000

Data Index: 308685 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.1812. Min Act: -0.0000

Data Index: 1443266 (Python Code)

Max Activating Token Index: 187

Text #12

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.2954. Min Act: -0.0000

Data Index: 418843 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1448670 (Python Code)

Max Activating Token Index: 530

Text #14

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.3077. Min Act: -0.0000

Data Index: 41062 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.2110. Min Act: -0.0000

Data Index: 281839 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.3013. Min Act: -0.0000

Data Index: 669053 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1644818 (Python Code)

Max Activating Token Index: 908

Text #18

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1569196 (Python Code)

Max Activating Token Index: 296

Text #19

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.2327. Min Act: -0.0000

Data Index: 630168 (C4 (Web Text))

Max Activating Token Index: 600