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

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

Neuron 1454 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0648. Min Range: -5.0648

Max Act: 5.0648. Min Act: -0.0000

Data Index: 363121 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.5145. Min Act: -0.0000

Data Index: 415948 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.5415. Min Act: -0.0000

Data Index: 1289496 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.4698. Min Act: -0.0000

Data Index: 821686 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.3889. Min Act: -0.0000

Data Index: 513532 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.5683. Min Act: -0.0000

Data Index: 1050898 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.2875. Min Act: -0.0000

Data Index: 372833 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.0060. Min Act: -0.0000

Data Index: 1061520 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.0986. Min Act: -0.0000

Data Index: 1039022 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.1006. Min Act: -0.0000

Data Index: 976104 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.3016. Min Act: -0.0000

Data Index: 18786 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.0663. Min Act: -0.0000

Data Index: 587279 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.2172. Min Act: -0.0000

Data Index: 110531 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.0190. Min Act: -0.0000

Data Index: 482521 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.0225. Min Act: -0.0000

Data Index: 567816 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 5.0648. Min Range: -5.0648

Max Act: 3.8600. Min Act: -0.0000

Data Index: 278997 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 5.0648. Min Range: -5.0648

Max Act: 3.8332. Min Act: -0.0000

Data Index: 240376 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 5.0648. Min Range: -5.0648

Max Act: 4.0230. Min Act: -0.0000

Data Index: 95720 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 5.0648. Min Range: -5.0648

Max Act: 3.9749. Min Act: -0.0000

Data Index: 847754 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 5.0648. Min Range: -5.0648

Max Act: 3.9325. Min Act: -0.0000

Data Index: 1063555 (C4 (Web Text))

Max Activating Token Index: 789