Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3879 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.6677. Min Act: -0.0000

Data Index: 10000 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1283920 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5098. Min Act: -0.0000

Data Index: 714633 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5400. Min Act: -0.0000

Data Index: 696392 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1144070 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5037. Min Act: -0.0000

Data Index: 559491 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4527. Min Act: -0.0000

Data Index: 639534 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4177. Min Act: -0.0000

Data Index: 393214 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1413551 (Python Code)

Max Activating Token Index: 937

Text #9

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1217318 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1573461 (Python Code)

Max Activating Token Index: 833

Text #11

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1189478 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4642. Min Act: -0.0000

Data Index: 263422 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4913. Min Act: -0.0000

Data Index: 469005 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4694. Min Act: -0.0000

Data Index: 621704 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4185. Min Act: -0.0001

Data Index: 1346676 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4145. Min Act: -0.0000

Data Index: 166612 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4001. Min Act: -0.0000

Data Index: 773493 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4052. Min Act: -0.0000

Data Index: 962751 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4293. Min Act: -0.0000

Data Index: 509274 (C4 (Web Text))

Max Activating Token Index: 334