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

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

Neuron 238 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.8155. Min Act: -0.0000

Data Index: 244707 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.7903. Min Act: -0.0000

Data Index: 744713 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.6032. Min Act: -0.0000

Data Index: 523179 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.2359. Min Act: -0.0000

Data Index: 52790 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.3325. Min Act: -0.0000

Data Index: 899581 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.2130. Min Act: -0.0000

Data Index: 39393 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.3055. Min Act: -0.0000

Data Index: 262903 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.2847. Min Act: -0.0000

Data Index: 1248889 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.0161. Min Act: -0.0000

Data Index: 1143552 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.2103. Min Act: -0.0000

Data Index: 539305 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.0567. Min Act: -0.0000

Data Index: 915793 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.0187. Min Act: -0.0000

Data Index: 492253 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.4727. Min Act: -0.0000

Data Index: 124622 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.0873. Min Act: -0.0000

Data Index: 333953 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.0330. Min Act: -0.0000

Data Index: 454811 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.9204. Min Act: -0.0000

Data Index: 329764 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.0497. Min Act: -0.0000

Data Index: 343128 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.2474. Min Act: -0.0000

Data Index: 664404 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.9804. Min Act: -0.0000

Data Index: 102877 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.8773. Min Act: -0.0000

Data Index: 282549 (C4 (Web Text))

Max Activating Token Index: 468