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

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

Neuron 67 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: 3.1614. Min Range: -3.1614

Max Act: 3.1614. Min Act: -0.0000

Data Index: 377809 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.3415. Min Act: -0.0000

Data Index: 206573 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.2818. Min Act: -0.0000

Data Index: 1165797 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.1533. Min Act: -0.0000

Data Index: 210617 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.8370. Min Act: -0.0000

Data Index: 599381 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.9916. Min Act: -0.0000

Data Index: 1344511 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 3.1614. Min Range: -3.1614

Max Act: 2.0530. Min Act: -0.0000

Data Index: 453284 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.8680. Min Act: -0.0000

Data Index: 229043 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.8470. Min Act: -0.0001

Data Index: 43302 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.7488. Min Act: -0.0000

Data Index: 805058 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.7201. Min Act: -0.0000

Data Index: 925432 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.8096. Min Act: -0.0000

Data Index: 1325363 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.7961. Min Act: -0.0000

Data Index: 573839 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.7939. Min Act: -0.0000

Data Index: 606391 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.7872. Min Act: -0.0000

Data Index: 1302666 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.5455. Min Act: -0.0000

Data Index: 844857 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.8512. Min Act: -0.0000

Data Index: 610739 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.6615. Min Act: -0.0000

Data Index: 638746 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.8521. Min Act: -0.0001

Data Index: 934773 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 3.1614. Min Range: -3.1614

Max Act: 1.6287. Min Act: -0.0001

Data Index: 472381 (C4 (Web Text))

Max Activating Token Index: 657