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

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

Neuron 4052 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0754. Min Range: -1.0754

Max Act: 1.0754. Min Act: -0.0001

Data Index: 64454 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.0754. Min Range: -1.0754

Max Act: 1.0147. Min Act: -0.0001

Data Index: 1261106 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.9261. Min Act: -0.0001

Data Index: 101098 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8207. Min Act: -0.0001

Data Index: 1551197 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.9775. Min Act: -0.0001

Data Index: 1134290 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7034. Min Act: -0.0001

Data Index: 1532025 (Python Code)

Max Activating Token Index: 370

Text #6

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7213. Min Act: -0.0001

Data Index: 1401446 (Python Code)

Max Activating Token Index: 162

Text #7

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6920. Min Act: -0.0001

Data Index: 153900 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7397. Min Act: -0.0001

Data Index: 1400084 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6901. Min Act: -0.0001

Data Index: 514721 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6884. Min Act: -0.0001

Data Index: 743284 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7105. Min Act: -0.0001

Data Index: 1353500 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7315. Min Act: -0.0001

Data Index: 1623715 (Python Code)

Max Activating Token Index: 258

Text #13

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7358. Min Act: -0.0001

Data Index: 1651248 (Python Code)

Max Activating Token Index: 231

Text #14

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7447. Min Act: -0.0001

Data Index: 1619331 (Python Code)

Max Activating Token Index: 50

Text #15

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6955. Min Act: -0.0001

Data Index: 881579 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7148. Min Act: -0.0001

Data Index: 1276802 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6944. Min Act: -0.0001

Data Index: 1453120 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7176. Min Act: -0.0001

Data Index: 1383951 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7143. Min Act: -0.0001

Data Index: 1629800 (Python Code)

Max Activating Token Index: 510