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

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

Neuron 3589 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: 2.7760. Min Range: -2.7760

Max Act: 2.7760. Min Act: -0.0000

Data Index: 365149 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.3072. Min Act: -0.0000

Data Index: 180754 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.3450. Min Act: -0.0000

Data Index: 787210 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.1570. Min Act: -0.0000

Data Index: 829433 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.2594. Min Act: -0.0000

Data Index: 1075398 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.0379. Min Act: -0.0000

Data Index: 23765 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.2282. Min Act: -0.0000

Data Index: 592244 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.2109. Min Act: -0.0000

Data Index: 270563 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.3553. Min Act: -0.0000

Data Index: 1082162 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.2922. Min Act: -0.0000

Data Index: 755359 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.8867. Min Act: -0.0000

Data Index: 655351 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.0824. Min Act: -0.0000

Data Index: 104900 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.0662. Min Act: -0.0000

Data Index: 867046 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.1849. Min Act: -0.0000

Data Index: 502097 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.0328. Min Act: -0.0000

Data Index: 656891 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 2.7760. Min Range: -2.7760

Max Act: 2.0984. Min Act: -0.0000

Data Index: 265740 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.8999. Min Act: -0.0000

Data Index: 1104094 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.7824. Min Act: -0.0000

Data Index: 286299 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.8842. Min Act: -0.0000

Data Index: 322012 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 2.7760. Min Range: -2.7760

Max Act: 1.9529. Min Act: -0.0000

Data Index: 973195 (C4 (Web Text))

Max Activating Token Index: 479