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

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

Neuron 4389 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8915. Min Range: -2.8915

Max Act: 2.8915. Min Act: -0.0000

Data Index: 1078394 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 2.8915. Min Range: -2.8915

Max Act: 2.5394. Min Act: -0.0000

Data Index: 663901 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 2.8915. Min Range: -2.8915

Max Act: 2.3636. Min Act: -0.0000

Data Index: 1022018 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 2.8915. Min Range: -2.8915

Max Act: 1.7460. Min Act: -0.0000

Data Index: 941959 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 2.8915. Min Range: -2.8915

Max Act: 2.0538. Min Act: -0.0000

Data Index: 570403 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 2.8915. Min Range: -2.8915

Max Act: 2.0969. Min Act: -0.0000

Data Index: 1522845 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 2.8915. Min Range: -2.8915

Max Act: 1.6789. Min Act: -0.0000

Data Index: 212832 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 2.8915. Min Range: -2.8915

Max Act: 2.0521. Min Act: -0.0000

Data Index: 461681 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 2.8915. Min Range: -2.8915

Max Act: 2.1588. Min Act: -0.0000

Data Index: 1273194 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 2.8915. Min Range: -2.8915

Max Act: 2.0353. Min Act: -0.0000

Data Index: 1139002 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 2.8915. Min Range: -2.8915

Max Act: 1.6570. Min Act: -0.0000

Data Index: 473073 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 2.8915. Min Range: -2.8915

Max Act: 1.8768. Min Act: -0.0000

Data Index: 130004 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 2.8915. Min Range: -2.8915

Max Act: 1.8507. Min Act: -0.0000

Data Index: 799121 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 2.8915. Min Range: -2.8915

Max Act: 1.8460. Min Act: -0.0000

Data Index: 1116766 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 2.8915. Min Range: -2.8915

Max Act: 1.8383. Min Act: -0.0000

Data Index: 469619 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 2.8915. Min Range: -2.8915

Max Act: 1.8203. Min Act: -0.0000

Data Index: 770581 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 2.8915. Min Range: -2.8915

Max Act: 1.8082. Min Act: -0.0000

Data Index: 967685 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 2.8915. Min Range: -2.8915

Max Act: 1.9092. Min Act: -0.0000

Data Index: 1037881 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 2.8915. Min Range: -2.8915

Max Act: 1.7667. Min Act: -0.0000

Data Index: 1433936 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 2.8915. Min Range: -2.8915

Max Act: 1.7657. Min Act: -0.0000

Data Index: 1137664 (C4 (Web Text))

Max Activating Token Index: 21