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

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

Neuron 481 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: 5.1391. Min Range: -5.1391

Max Act: 5.1391. Min Act: -0.0001

Data Index: 1132065 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.9076. Min Act: -0.0001

Data Index: 1197733 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.8472. Min Act: -0.0001

Data Index: 1553203 (Python Code)

Max Activating Token Index: 168

Text #3

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.8044. Min Act: -0.0001

Data Index: 1025121 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.4871. Min Act: -0.0001

Data Index: 1066009 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.4439. Min Act: -0.0001

Data Index: 1588630 (Python Code)

Max Activating Token Index: 520

Text #6

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.5720. Min Act: -0.0001

Data Index: 1459110 (Python Code)

Max Activating Token Index: 826

Text #7

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.4377. Min Act: -0.0001

Data Index: 1037408 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.4002. Min Act: -0.0001

Data Index: 624556 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.2091. Min Act: -0.0001

Data Index: 1627096 (Python Code)

Max Activating Token Index: 683

Text #10

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.4880. Min Act: -0.0001

Data Index: 1306736 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.3332. Min Act: -0.0001

Data Index: 1370425 (Python Code)

Max Activating Token Index: 636

Text #12

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.3148. Min Act: -0.0001

Data Index: 283114 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.2847. Min Act: -0.0001

Data Index: 1571226 (Python Code)

Max Activating Token Index: 641

Text #14

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.2634. Min Act: -0.0001

Data Index: 916062 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.2743. Min Act: -0.0001

Data Index: 1449996 (Python Code)

Max Activating Token Index: 803

Text #16

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.0928. Min Act: -0.0001

Data Index: 1372638 (Python Code)

Max Activating Token Index: 89

Text #17

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.2575. Min Act: -0.0001

Data Index: 152280 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.0848. Min Act: -0.0001

Data Index: 1436196 (Python Code)

Max Activating Token Index: 154

Text #19

Max Range: 5.1391. Min Range: -5.1391

Max Act: 4.0544. Min Act: -0.0001

Data Index: 1139041 (C4 (Web Text))

Max Activating Token Index: 348