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

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

Neuron 5866 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9815. Min Range: -4.9815

Max Act: 4.9815. Min Act: -0.0000

Data Index: 825524 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 4.9815. Min Range: -4.9815

Max Act: 4.5667. Min Act: -0.0000

Data Index: 1349958 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 4.9815. Min Range: -4.9815

Max Act: 4.5807. Min Act: -0.0000

Data Index: 397544 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 4.9815. Min Range: -4.9815

Max Act: 4.3418. Min Act: -0.0000

Data Index: 430656 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.9662. Min Act: -0.0000

Data Index: 694569 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.9333. Min Act: -0.0000

Data Index: 272087 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.6812. Min Act: -0.0000

Data Index: 623382 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.3614. Min Act: -0.0000

Data Index: 1284707 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.4622. Min Act: -0.0000

Data Index: 1213797 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.2392. Min Act: -0.0000

Data Index: 253064 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.3231. Min Act: -0.0000

Data Index: 380322 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.1337. Min Act: -0.0000

Data Index: 1182895 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.4089. Min Act: -0.0000

Data Index: 932749 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.0056. Min Act: -0.0000

Data Index: 1254336 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.2607. Min Act: -0.0000

Data Index: 35290 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.1013. Min Act: -0.0000

Data Index: 488039 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.0789. Min Act: -0.0000

Data Index: 310638 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.1976. Min Act: -0.0000

Data Index: 1230556 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.0433. Min Act: -0.0000

Data Index: 1029703 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 4.9815. Min Range: -4.9815

Max Act: 3.1002. Min Act: -0.0000

Data Index: 924246 (C4 (Web Text))

Max Activating Token Index: 474