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

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

Neuron 2097 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1512. Min Range: -2.1512

Max Act: 2.1512. Min Act: -0.0000

Data Index: 1221160 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 2.1512. Min Range: -2.1512

Max Act: 2.0971. Min Act: -0.0000

Data Index: 305624 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 2.1512. Min Range: -2.1512

Max Act: 2.1220. Min Act: -0.0000

Data Index: 959096 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.8506. Min Act: -0.0000

Data Index: 33912 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.8408. Min Act: -0.0000

Data Index: 929702 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.8379. Min Act: -0.0000

Data Index: 197173 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.8195. Min Act: -0.0000

Data Index: 848918 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.7227. Min Act: -0.0000

Data Index: 923586 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.7209. Min Act: -0.0000

Data Index: 167842 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.7936. Min Act: -0.0000

Data Index: 711129 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6861. Min Act: -0.0000

Data Index: 944796 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.7628. Min Act: -0.0000

Data Index: 983511 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.8581. Min Act: -0.0000

Data Index: 321602 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.7530. Min Act: -0.0000

Data Index: 686705 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6589. Min Act: -0.0000

Data Index: 67075 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6482. Min Act: -0.0000

Data Index: 657243 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6351. Min Act: -0.0000

Data Index: 99633 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.5218. Min Act: -0.0000

Data Index: 850772 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6129. Min Act: -0.0000

Data Index: 1648531 (Python Code)

Max Activating Token Index: 269

Text #19

Max Range: 2.1512. Min Range: -2.1512

Max Act: 1.6098. Min Act: -0.0000

Data Index: 1165585 (C4 (Web Text))

Max Activating Token Index: 701