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

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

Neuron 3468 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3878. Min Act: -0.0000

Data Index: 316035 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1225767 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3898. Min Act: -0.0000

Data Index: 923821 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3314. Min Act: -0.0000

Data Index: 395947 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3499. Min Act: -0.0000

Data Index: 978669 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3418. Min Act: -0.0000

Data Index: 601662 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3368. Min Act: -0.0000

Data Index: 82283 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1146177 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1167775 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3232. Min Act: -0.0000

Data Index: 258815 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1123246 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3188. Min Act: 0.0000

Data Index: 1267771 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3210. Min Act: 0.0000

Data Index: 797390 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.2893. Min Act: -0.0000

Data Index: 172342 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.2849. Min Act: -0.0000

Data Index: 525257 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.2866. Min Act: 0.0000

Data Index: 969541 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.2853. Min Act: -0.0000

Data Index: 744399 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.2838. Min Act: -0.0000

Data Index: 172315 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.2833. Min Act: -0.0000

Data Index: 676052 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.2816. Min Act: 0.0000

Data Index: 1298388 (C4 (Web Text))

Max Activating Token Index: 878