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

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

Neuron 2616 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: 7.4836. Min Range: -7.4836

Max Act: 7.4836. Min Act: -0.0000

Data Index: 934148 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 7.4836. Min Range: -7.4836

Max Act: 7.2693. Min Act: -0.0000

Data Index: 595150 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 7.4836. Min Range: -7.4836

Max Act: 7.1756. Min Act: -0.0000

Data Index: 885588 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.9771. Min Act: -0.0000

Data Index: 644143 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 7.4836. Min Range: -7.4836

Max Act: 7.2545. Min Act: -0.0000

Data Index: 197102 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 7.4836. Min Range: -7.4836

Max Act: 7.0013. Min Act: -0.0000

Data Index: 1209652 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.7740. Min Act: -0.0000

Data Index: 348800 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.7589. Min Act: -0.0000

Data Index: 650799 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.6268. Min Act: -0.0000

Data Index: 1244049 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.3729. Min Act: -0.0000

Data Index: 913131 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.5604. Min Act: -0.0000

Data Index: 765902 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.3600. Min Act: -0.0000

Data Index: 591544 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.6129. Min Act: -0.0000

Data Index: 486437 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.1387. Min Act: -0.0000

Data Index: 833864 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.1089. Min Act: -0.0000

Data Index: 154212 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.4011. Min Act: -0.0000

Data Index: 70608 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.0018. Min Act: -0.0000

Data Index: 1128400 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 7.4836. Min Range: -7.4836

Max Act: 5.9931. Min Act: -0.0000

Data Index: 1192758 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 7.4836. Min Range: -7.4836

Max Act: 6.1451. Min Act: -0.0000

Data Index: 173571 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 7.4836. Min Range: -7.4836

Max Act: 5.9417. Min Act: -0.0000

Data Index: 615156 (C4 (Web Text))

Max Activating Token Index: 949