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

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

Neuron 5143 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0799. Min Range: -1.0799

Max Act: 1.0799. Min Act: -0.0000

Data Index: 300697 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.9964. Min Act: -0.0000

Data Index: 430818 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.8825. Min Act: -0.0000

Data Index: 802304 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.6875. Min Act: -0.0000

Data Index: 128990 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.6218. Min Act: -0.0000

Data Index: 828554 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.7684. Min Act: -0.0001

Data Index: 1350178 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.6513. Min Act: -0.0001

Data Index: 1015372 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.6481. Min Act: -0.0001

Data Index: 116200 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1459438 (Python Code)

Max Activating Token Index: 602

Text #9

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.5929. Min Act: -0.0001

Data Index: 1268898 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.5865. Min Act: -0.0001

Data Index: 524485 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.6269. Min Act: -0.0000

Data Index: 316018 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1065438 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.5601. Min Act: -0.0000

Data Index: 633497 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1462219 (Python Code)

Max Activating Token Index: 625

Text #15

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.5530. Min Act: -0.0000

Data Index: 583304 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1436104 (Python Code)

Max Activating Token Index: 604

Text #17

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1365556 (Python Code)

Max Activating Token Index: 701

Text #18

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.5455. Min Act: -0.0001

Data Index: 1254103 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.5251. Min Act: -0.0000

Data Index: 584739 (C4 (Web Text))

Max Activating Token Index: 950