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

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

Neuron 857 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.3793. Min Act: -0.0000

Data Index: 1284699 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.3114. Min Act: -0.0000

Data Index: 782168 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.1500. Min Act: -0.0000

Data Index: 1341019 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.3853. Min Act: -0.0000

Data Index: 418152 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1293320 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.1825. Min Act: -0.0000

Data Index: 119635 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.0702. Min Act: -0.0000

Data Index: 571770 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.2227. Min Act: -0.0000

Data Index: 117160 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.1794. Min Act: -0.0000

Data Index: 710892 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1002930 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.8699. Min Act: -0.0000

Data Index: 40597 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.7394. Min Act: -0.0000

Data Index: 118862 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.7452. Min Act: -0.0000

Data Index: 579864 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.8617. Min Act: -0.0000

Data Index: 348355 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.7490. Min Act: -0.0000

Data Index: 564739 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.6646. Min Act: -0.0000

Data Index: 853035 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.7152. Min Act: -0.0000

Data Index: 284104 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1052321 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.7241. Min Act: -0.0000

Data Index: 733265 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.6176. Min Act: -0.0000

Data Index: 919532 (C4 (Web Text))

Max Activating Token Index: 814