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

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

Neuron 5195 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: 4.9606. Min Range: -4.9606

Max Act: 4.9606. Min Act: -0.0000

Data Index: 1013604 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.5364. Min Act: -0.0000

Data Index: 469393 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.3315. Min Act: -0.0000

Data Index: 22128 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.4910. Min Act: -0.0000

Data Index: 1225945 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.6674. Min Act: -0.0000

Data Index: 41649 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.4802. Min Act: -0.0000

Data Index: 455804 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.2921. Min Act: -0.0000

Data Index: 649486 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.1026. Min Act: -0.0000

Data Index: 1024751 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.2487. Min Act: -0.0000

Data Index: 593900 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.2009. Min Act: -0.0000

Data Index: 854477 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.1818. Min Act: -0.0000

Data Index: 1251774 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.2131. Min Act: -0.0000

Data Index: 68830 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.1665. Min Act: -0.0000

Data Index: 183280 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.4986. Min Act: -0.0000

Data Index: 34352 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.2855. Min Act: -0.0000

Data Index: 384420 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.3210. Min Act: -0.0000

Data Index: 954189 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.2736. Min Act: -0.0000

Data Index: 341899 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.6426. Min Act: -0.0000

Data Index: 711667 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 4.9606. Min Range: -4.9606

Max Act: 3.9133. Min Act: -0.0000

Data Index: 265428 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 4.9606. Min Range: -4.9606

Max Act: 4.2455. Min Act: -0.0000

Data Index: 177800 (C4 (Web Text))

Max Activating Token Index: 387