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

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

Neuron 2664 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: 1.9285. Min Range: -1.9285

Max Act: 1.9285. Min Act: -0.0000

Data Index: 1149386 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.8432. Min Act: -0.0000

Data Index: 687387 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.7261. Min Act: -0.0000

Data Index: 933150 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.6942. Min Act: -0.0000

Data Index: 225665 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.7996. Min Act: -0.0000

Data Index: 1470384 (Python Code)

Max Activating Token Index: 201

Text #5

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.5709. Min Act: -0.0000

Data Index: 1394953 (Python Code)

Max Activating Token Index: 948

Text #6

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.5590. Min Act: -0.0000

Data Index: 7046 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.4544. Min Act: -0.0000

Data Index: 1071754 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.5438. Min Act: -0.0000

Data Index: 1499245 (Python Code)

Max Activating Token Index: 661

Text #9

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.6304. Min Act: -0.0000

Data Index: 1204180 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.5063. Min Act: -0.0000

Data Index: 531800 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.3079. Min Act: -0.0000

Data Index: 994907 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.3581. Min Act: -0.0000

Data Index: 359541 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.3428. Min Act: -0.0000

Data Index: 749101 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.3259. Min Act: -0.0000

Data Index: 1527977 (Python Code)

Max Activating Token Index: 937

Text #15

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1631867 (Python Code)

Max Activating Token Index: 311

Text #16

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.2930. Min Act: -0.0000

Data Index: 60171 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.2922. Min Act: -0.0000

Data Index: 351851 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.3584. Min Act: -0.0000

Data Index: 294441 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 1.9285. Min Range: -1.9285

Max Act: 1.2119. Min Act: -0.0000

Data Index: 1424945 (Python Code)

Max Activating Token Index: 345