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

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

Neuron 3646 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1647. Min Range: -2.1647

Max Act: 2.1647. Min Act: -0.0000

Data Index: 924371 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.8678. Min Act: -0.0000

Data Index: 994856 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.4950. Min Act: -0.0000

Data Index: 434538 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.3136. Min Act: -0.0000

Data Index: 227064 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.2814. Min Act: -0.0000

Data Index: 295437 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.1548. Min Act: -0.0000

Data Index: 1136468 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.1603. Min Act: -0.0000

Data Index: 918748 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.1397. Min Act: -0.0000

Data Index: 394267 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.1193. Min Act: -0.0000

Data Index: 45107 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.0921. Min Act: -0.0000

Data Index: 786552 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.0804. Min Act: -0.0000

Data Index: 1237833 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.0498. Min Act: -0.0000

Data Index: 128300 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.1214. Min Act: -0.0000

Data Index: 282040 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.0426. Min Act: -0.0000

Data Index: 754570 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.0251. Min Act: -0.0000

Data Index: 521066 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.0399. Min Act: -0.0000

Data Index: 805108 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.0541. Min Act: -0.0000

Data Index: 699646 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.0141. Min Act: -0.0000

Data Index: 379798 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.0384. Min Act: -0.0000

Data Index: 929836 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 2.1647. Min Range: -2.1647

Max Act: 1.0366. Min Act: -0.0000

Data Index: 591365 (C4 (Web Text))

Max Activating Token Index: 495