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

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

Neuron 3174 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: 1.8745. Min Range: -1.8745

Max Act: 1.8735. Min Act: -0.0000

Data Index: 994244 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.8745. Min Act: -0.0000

Data Index: 1050606 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.7122. Min Act: -0.0000

Data Index: 927933 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.5775. Min Act: -0.0000

Data Index: 58049 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.4531. Min Act: -0.0000

Data Index: 996502 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.4401. Min Act: -0.0000

Data Index: 1183488 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.4429. Min Act: -0.0000

Data Index: 419586 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.6063. Min Act: -0.0000

Data Index: 915226 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.5908. Min Act: -0.0000

Data Index: 9822 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.4925. Min Act: -0.0000

Data Index: 344083 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.6413. Min Act: -0.0000

Data Index: 621545 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1090907 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.4138. Min Act: -0.0000

Data Index: 38214 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.4356. Min Act: -0.0000

Data Index: 137398 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.4770. Min Act: -0.0000

Data Index: 1218965 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.3066. Min Act: -0.0000

Data Index: 349105 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.2253. Min Act: -0.0000

Data Index: 1252033 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.3964. Min Act: -0.0000

Data Index: 1555537 (Python Code)

Max Activating Token Index: 55

Text #18

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.4483. Min Act: -0.0000

Data Index: 927610 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.3200. Min Act: -0.0000

Data Index: 276426 (C4 (Web Text))

Max Activating Token Index: 183