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

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

Neuron 655 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8897. Min Range: -5.8897

Max Act: 5.8897. Min Act: -0.0000

Data Index: 229154 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 5.8897. Min Range: -5.8897

Max Act: 5.5663. Min Act: -0.0000

Data Index: 256029 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 5.8897. Min Range: -5.8897

Max Act: 5.2741. Min Act: -0.0000

Data Index: 935839 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 5.8897. Min Range: -5.8897

Max Act: 5.1397. Min Act: -0.0000

Data Index: 25645 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 5.8897. Min Range: -5.8897

Max Act: 5.2010. Min Act: -0.0000

Data Index: 977050 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.9499. Min Act: -0.0000

Data Index: 17748 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.6569. Min Act: -0.0000

Data Index: 34896 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.4788. Min Act: -0.0000

Data Index: 1086730 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.8049. Min Act: -0.0000

Data Index: 498181 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.7643. Min Act: -0.0000

Data Index: 747698 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.4028. Min Act: -0.0000

Data Index: 1011956 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.6515. Min Act: -0.0000

Data Index: 718762 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.5499. Min Act: -0.0000

Data Index: 311797 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.3497. Min Act: -0.0000

Data Index: 228643 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.5300. Min Act: -0.0000

Data Index: 813572 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.3073. Min Act: -0.0000

Data Index: 813936 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.2451. Min Act: -0.0000

Data Index: 898958 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.4150. Min Act: -0.0000

Data Index: 1002666 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.1820. Min Act: -0.0000

Data Index: 724317 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 5.8897. Min Range: -5.8897

Max Act: 4.3829. Min Act: -0.0000

Data Index: 1351544 (C4 (Web Text))

Max Activating Token Index: 569