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

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

Neuron 1482 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: 4.5112. Min Range: -4.5112

Max Act: 4.5112. Min Act: -0.0000

Data Index: 725607 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 4.5112. Min Range: -4.5112

Max Act: 4.0554. Min Act: -0.0000

Data Index: 465940 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 4.5112. Min Range: -4.5112

Max Act: 4.0874. Min Act: -0.0000

Data Index: 840310 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.8660. Min Act: -0.0000

Data Index: 1145425 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.8619. Min Act: -0.0000

Data Index: 270138 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.7687. Min Act: -0.0000

Data Index: 1322568 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.7072. Min Act: -0.0000

Data Index: 1290972 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.5319. Min Act: -0.0000

Data Index: 1112414 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.8621. Min Act: -0.0000

Data Index: 551720 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.7778. Min Act: -0.0000

Data Index: 80373 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.4643. Min Act: -0.0000

Data Index: 1338899 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.6101. Min Act: -0.0000

Data Index: 606191 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.5291. Min Act: -0.0000

Data Index: 536898 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.5307. Min Act: -0.0000

Data Index: 959066 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.3442. Min Act: -0.0000

Data Index: 805740 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.4896. Min Act: -0.0000

Data Index: 1199890 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.4181. Min Act: -0.0000

Data Index: 641499 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.2741. Min Act: -0.0000

Data Index: 629096 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.3774. Min Act: -0.0000

Data Index: 524099 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 4.5112. Min Range: -4.5112

Max Act: 3.5423. Min Act: -0.0000

Data Index: 85033 (C4 (Web Text))

Max Activating Token Index: 942