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

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

Neuron 5183 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.8648. Min Act: -0.0000

Data Index: 479994 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.0253. Min Act: -0.0000

Data Index: 533686 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.9849. Min Act: -0.0000

Data Index: 703199 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.0760. Min Act: -0.0000

Data Index: 1036299 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.5766. Min Act: -0.0000

Data Index: 1542677 (Python Code)

Max Activating Token Index: 540

Text #5

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.9764. Min Act: -0.0000

Data Index: 1214187 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.6853. Min Act: -0.0000

Data Index: 837140 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.5056. Min Act: -0.0000

Data Index: 1062597 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.4621. Min Act: -0.0000

Data Index: 158800 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.2960. Min Act: -0.0000

Data Index: 665003 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.0003. Min Act: -0.0000

Data Index: 144538 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.4753. Min Act: -0.0000

Data Index: 675001 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.0968. Min Act: -0.0000

Data Index: 87439 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.1892. Min Act: -0.0000

Data Index: 437522 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.2768. Min Act: -0.0000

Data Index: 1238476 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.2456. Min Act: -0.0000

Data Index: 1158952 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.2498. Min Act: -0.0000

Data Index: 602462 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.2588. Min Act: -0.0000

Data Index: 490479 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.2480. Min Act: -0.0000

Data Index: 252085 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.0083. Min Act: -0.0000

Data Index: 269265 (C4 (Web Text))

Max Activating Token Index: 351