Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5198 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.6854. Min Act: -0.0000

Data Index: 798519 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.6565. Min Act: -0.0000

Data Index: 319674 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.6193. Min Act: -0.0000

Data Index: 708547 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5869. Min Act: -0.0000

Data Index: 364098 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1353459 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1352693 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5554. Min Act: -0.0000

Data Index: 284287 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5492. Min Act: -0.0000

Data Index: 874591 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4852. Min Act: -0.0000

Data Index: 986349 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5192. Min Act: -0.0000

Data Index: 570100 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5125. Min Act: -0.0000

Data Index: 912845 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5196. Min Act: -0.0000

Data Index: 463556 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4623. Min Act: -0.0000

Data Index: 571483 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1283902 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4572. Min Act: -0.0000

Data Index: 263703 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4534. Min Act: -0.0000

Data Index: 648098 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4800. Min Act: -0.0000

Data Index: 342384 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4285. Min Act: 0.0000

Data Index: 770104 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4265. Min Act: -0.0000

Data Index: 137937 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1292464 (C4 (Web Text))

Max Activating Token Index: 791