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

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

Neuron 955 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9164. Min Range: -6.9164

Max Act: 6.7130. Min Act: -0.0000

Data Index: 1266377 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 6.9164. Min Range: -6.9164

Max Act: 6.9164. Min Act: -0.0000

Data Index: 853475 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 6.9164. Min Range: -6.9164

Max Act: 6.8703. Min Act: -0.0000

Data Index: 849143 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 6.9164. Min Range: -6.9164

Max Act: 6.8949. Min Act: -0.0000

Data Index: 902986 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 6.9164. Min Range: -6.9164

Max Act: 5.9240. Min Act: -0.0000

Data Index: 866606 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 6.9164. Min Range: -6.9164

Max Act: 5.9125. Min Act: -0.0000

Data Index: 601841 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 6.9164. Min Range: -6.9164

Max Act: 5.8437. Min Act: -0.0000

Data Index: 742291 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 6.9164. Min Range: -6.9164

Max Act: 5.8457. Min Act: -0.0000

Data Index: 203937 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 6.9164. Min Range: -6.9164

Max Act: 5.7389. Min Act: -0.0000

Data Index: 264405 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 6.9164. Min Range: -6.9164

Max Act: 5.8389. Min Act: -0.0000

Data Index: 864960 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 6.9164. Min Range: -6.9164

Max Act: 5.2453. Min Act: -0.0000

Data Index: 809606 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 6.9164. Min Range: -6.9164

Max Act: 5.0387. Min Act: -0.0000

Data Index: 378628 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 6.9164. Min Range: -6.9164

Max Act: 4.8650. Min Act: -0.0000

Data Index: 1204781 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 6.9164. Min Range: -6.9164

Max Act: 4.9408. Min Act: -0.0000

Data Index: 559131 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 6.9164. Min Range: -6.9164

Max Act: 4.5277. Min Act: -0.0000

Data Index: 1036042 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 6.9164. Min Range: -6.9164

Max Act: 4.6243. Min Act: -0.0000

Data Index: 488202 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 6.9164. Min Range: -6.9164

Max Act: 4.6087. Min Act: -0.0000

Data Index: 1102823 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 6.9164. Min Range: -6.9164

Max Act: 4.3279. Min Act: -0.0000

Data Index: 359354 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 6.9164. Min Range: -6.9164

Max Act: 4.0650. Min Act: -0.0000

Data Index: 910281 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 6.9164. Min Range: -6.9164

Max Act: 4.0723. Min Act: -0.0000

Data Index: 825401 (C4 (Web Text))

Max Activating Token Index: 39