Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2876 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.2051. Min Act: -0.0003

Data Index: 1060653 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.2147. Min Act: -0.0003

Data Index: 491950 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.2495. Min Act: -0.0003

Data Index: 415445 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.0085. Min Act: -0.0003

Data Index: 320953 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.9754. Min Act: -0.0003

Data Index: 606418 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.9892. Min Act: -0.0003

Data Index: 808967 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.9550. Min Act: -0.0003

Data Index: 919685 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.8409. Min Act: -0.0003

Data Index: 588862 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.8649. Min Act: -0.0003

Data Index: 1346390 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.7366. Min Act: -0.0003

Data Index: 234221 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.8946. Min Act: -0.0003

Data Index: 646255 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.9500. Min Act: -0.0003

Data Index: 339080 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.7106. Min Act: -0.0003

Data Index: 483069 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.8550. Min Act: -0.0003

Data Index: 1167525 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.8998. Min Act: -0.0003

Data Index: 1265442 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.6810. Min Act: -0.0003

Data Index: 1307368 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.0349. Min Act: -0.0003

Data Index: 503440 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.7357. Min Act: -0.0003

Data Index: 322393 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.7900. Min Act: -0.0003

Data Index: 565421 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.8401. Min Act: -0.0003

Data Index: 469619 (C4 (Web Text))

Max Activating Token Index: 155