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

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

Neuron 58 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: 1.7533. Min Range: -1.7533

Max Act: 1.7533. Min Act: -0.0000

Data Index: 469662 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.6934. Min Act: -0.0000

Data Index: 217509 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.6691. Min Act: -0.0000

Data Index: 1063385 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.6623. Min Act: -0.0001

Data Index: 175996 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.6238. Min Act: -0.0000

Data Index: 971871 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.7019. Min Act: -0.0000

Data Index: 472904 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.6464. Min Act: -0.0000

Data Index: 904779 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.5089. Min Act: -0.0000

Data Index: 178045 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.6170. Min Act: -0.0000

Data Index: 1285207 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.5521. Min Act: -0.0000

Data Index: 376651 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.5846. Min Act: -0.0000

Data Index: 263886 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.5376. Min Act: -0.0000

Data Index: 1305345 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.4873. Min Act: -0.0000

Data Index: 83387 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.5125. Min Act: -0.0000

Data Index: 1245698 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.5142. Min Act: -0.0000

Data Index: 12730 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.5561. Min Act: -0.0000

Data Index: 605172 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.4445. Min Act: -0.0000

Data Index: 576849 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.4818. Min Act: -0.0000

Data Index: 394467 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.4421. Min Act: -0.0000

Data Index: 130462 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 1.7533. Min Range: -1.7533

Max Act: 1.4428. Min Act: -0.0000

Data Index: 964929 (C4 (Web Text))

Max Activating Token Index: 468