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

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

Neuron 5868 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.8436. Min Act: -0.0000

Data Index: 581358 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.7167. Min Act: -0.0000

Data Index: 30325 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.6823. Min Act: -0.0000

Data Index: 1109536 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.6047. Min Act: -0.0000

Data Index: 1359222 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.1622. Min Act: -0.0000

Data Index: 630447 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.2550. Min Act: -0.0000

Data Index: 426194 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 4.8436. Min Range: -4.8436

Max Act: 3.9124. Min Act: -0.0000

Data Index: 832633 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.0810. Min Act: -0.0000

Data Index: 868714 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.0713. Min Act: -0.0000

Data Index: 1311926 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 4.8436. Min Range: -4.8436

Max Act: 3.8803. Min Act: -0.0000

Data Index: 1084804 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.0173. Min Act: -0.0000

Data Index: 683219 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 4.8436. Min Range: -4.8436

Max Act: 3.9963. Min Act: -0.0000

Data Index: 54606 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.1465. Min Act: -0.0000

Data Index: 637452 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 4.8436. Min Range: -4.8436

Max Act: 3.9573. Min Act: -0.0000

Data Index: 644205 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 4.8436. Min Range: -4.8436

Max Act: 3.9655. Min Act: -0.0000

Data Index: 268487 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 4.8436. Min Range: -4.8436

Max Act: 3.7508. Min Act: -0.0000

Data Index: 195886 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.0684. Min Act: -0.0000

Data Index: 1093081 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 4.8436. Min Range: -4.8436

Max Act: 3.8835. Min Act: -0.0000

Data Index: 1296607 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 4.8436. Min Range: -4.8436

Max Act: 3.8906. Min Act: -0.0000

Data Index: 804707 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 4.8436. Min Range: -4.8436

Max Act: 3.8824. Min Act: -0.0000

Data Index: 747653 (C4 (Web Text))

Max Activating Token Index: 624