Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3957 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.7571. Min Act: -0.0001

Data Index: 672949 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.7785. Min Act: -0.0001

Data Index: 58448 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.7574. Min Act: -0.0001

Data Index: 946655 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.6017. Min Act: -0.0001

Data Index: 1349726 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.6855. Min Act: -0.0001

Data Index: 1188720 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.6511. Min Act: -0.0001

Data Index: 719565 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.6672. Min Act: -0.0001

Data Index: 86415 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.5822. Min Act: -0.0001

Data Index: 1325946 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.5417. Min Act: -0.0001

Data Index: 870875 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.5943. Min Act: -0.0001

Data Index: 1290203 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.5393. Min Act: -0.0001

Data Index: 435176 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.5569. Min Act: -0.0001

Data Index: 972130 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.5688. Min Act: -0.0001

Data Index: 616960 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.5753. Min Act: -0.0001

Data Index: 718302 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.5688. Min Act: -0.0001

Data Index: 383220 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.5955. Min Act: -0.0001

Data Index: 1068858 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.5416. Min Act: -0.0001

Data Index: 997638 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.4722. Min Act: -0.0001

Data Index: 286946 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.5332. Min Act: -0.0001

Data Index: 1357032 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.7785. Min Range: -0.7785

Max Act: 0.5667. Min Act: -0.0001

Data Index: 1329403 (C4 (Web Text))

Max Activating Token Index: 1008