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

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

Neuron 1402 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: 4.1001. Min Range: -4.1001

Max Act: 4.1001. Min Act: -0.0000

Data Index: 635832 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.7582. Min Act: -0.0000

Data Index: 119987 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.7090. Min Act: -0.0000

Data Index: 497899 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.5625. Min Act: -0.0001

Data Index: 191000 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.8688. Min Act: -0.0001

Data Index: 801591 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.5055. Min Act: -0.0001

Data Index: 69794 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.3203. Min Act: -0.0000

Data Index: 676024 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.4094. Min Act: -0.0001

Data Index: 438087 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.1431. Min Act: -0.0000

Data Index: 955725 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.1473. Min Act: -0.0001

Data Index: 579848 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 4.1001. Min Range: -4.1001

Max Act: 2.9551. Min Act: -0.0000

Data Index: 611932 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.0883. Min Act: -0.0001

Data Index: 955553 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.3721. Min Act: -0.0000

Data Index: 885396 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.0667. Min Act: -0.0000

Data Index: 1305242 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.0718. Min Act: -0.0001

Data Index: 841345 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 4.1001. Min Range: -4.1001

Max Act: 2.8107. Min Act: -0.0000

Data Index: 731458 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 4.1001. Min Range: -4.1001

Max Act: 2.8113. Min Act: -0.0001

Data Index: 8355 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 4.1001. Min Range: -4.1001

Max Act: 2.9566. Min Act: -0.0001

Data Index: 1129183 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 4.1001. Min Range: -4.1001

Max Act: 3.0495. Min Act: -0.0001

Data Index: 1232370 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 4.1001. Min Range: -4.1001

Max Act: 2.8875. Min Act: -0.0001

Data Index: 1289835 (C4 (Web Text))

Max Activating Token Index: 416