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

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

Neuron 1516 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.7139. Min Act: -0.0000

Data Index: 25786 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.7566. Min Act: -0.0000

Data Index: 110694 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.2220. Min Act: -0.0000

Data Index: 772910 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.3493. Min Act: -0.0000

Data Index: 797930 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.3339. Min Act: -0.0000

Data Index: 1237165 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.2041. Min Act: -0.0000

Data Index: 898010 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.3024. Min Act: -0.0000

Data Index: 1002481 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.4065. Min Act: -0.0000

Data Index: 463551 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.1842. Min Act: -0.0000

Data Index: 994090 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.2752. Min Act: -0.0000

Data Index: 365386 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.1612. Min Act: -0.0000

Data Index: 349765 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.2641. Min Act: -0.0000

Data Index: 611589 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.2758. Min Act: -0.0000

Data Index: 739238 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.1240. Min Act: -0.0000

Data Index: 358333 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.2247. Min Act: -0.0000

Data Index: 1125245 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.2076. Min Act: -0.0000

Data Index: 179500 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.2084. Min Act: -0.0000

Data Index: 153596 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.1918. Min Act: -0.0000

Data Index: 77220 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.3079. Min Act: -0.0000

Data Index: 994773 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 2.7566. Min Range: -2.7566

Max Act: 2.0745. Min Act: -0.0000

Data Index: 982444 (C4 (Web Text))

Max Activating Token Index: 836