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

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

Neuron 585 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.6791. Min Act: -0.0000

Data Index: 704793 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.4305. Min Act: -0.0000

Data Index: 1142377 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.1123. Min Act: -0.0000

Data Index: 64687 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.2252. Min Act: -0.0000

Data Index: 537904 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.2864. Min Act: -0.0000

Data Index: 699962 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.3244. Min Act: -0.0000

Data Index: 87841 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.0503. Min Act: -0.0000

Data Index: 697389 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.1483. Min Act: -0.0000

Data Index: 202548 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.2500. Min Act: -0.0000

Data Index: 211488 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.1317. Min Act: -0.0000

Data Index: 563185 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.0070. Min Act: -0.0000

Data Index: 1640359 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.3139. Min Act: -0.0000

Data Index: 751983 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.1800. Min Act: -0.0000

Data Index: 582315 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 2.6791. Min Range: -2.6791

Max Act: 1.9491. Min Act: -0.0000

Data Index: 1105134 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.1722. Min Act: -0.0000

Data Index: 310769 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.0308. Min Act: -0.0000

Data Index: 702901 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.0303. Min Act: -0.0000

Data Index: 991557 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.1179. Min Act: -0.0000

Data Index: 956467 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 2.6791. Min Range: -2.6791

Max Act: 2.0006. Min Act: -0.0000

Data Index: 1599581 (Python Code)

Max Activating Token Index: 417

Text #19

Max Range: 2.6791. Min Range: -2.6791

Max Act: 1.8917. Min Act: -0.0000

Data Index: 1179625 (C4 (Web Text))

Max Activating Token Index: 73