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

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

Neuron 4358 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: 5.3871. Min Range: -5.3871

Max Act: 5.3871. Min Act: -0.0000

Data Index: 44828 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 5.3871. Min Range: -5.3871

Max Act: 4.0529. Min Act: -0.0000

Data Index: 26787 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 5.3871. Min Range: -5.3871

Max Act: 3.8032. Min Act: -0.0000

Data Index: 1179386 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 5.3871. Min Range: -5.3871

Max Act: 3.3092. Min Act: -0.0000

Data Index: 512076 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 5.3871. Min Range: -5.3871

Max Act: 3.4073. Min Act: -0.0000

Data Index: 207297 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 5.3871. Min Range: -5.3871

Max Act: 3.2404. Min Act: -0.0000

Data Index: 436033 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 5.3871. Min Range: -5.3871

Max Act: 3.2079. Min Act: -0.0000

Data Index: 231694 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 5.3871. Min Range: -5.3871

Max Act: 3.2075. Min Act: -0.0000

Data Index: 951313 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 5.3871. Min Range: -5.3871

Max Act: 3.2114. Min Act: 0.0000

Data Index: 1052905 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 5.3871. Min Range: -5.3871

Max Act: 3.1578. Min Act: -0.0000

Data Index: 216434 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 5.3871. Min Range: -5.3871

Max Act: 3.4036. Min Act: -0.0000

Data Index: 1252092 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 5.3871. Min Range: -5.3871

Max Act: 3.0478. Min Act: -0.0000

Data Index: 925408 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 5.3871. Min Range: -5.3871

Max Act: 2.9860. Min Act: -0.0000

Data Index: 692470 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 5.3871. Min Range: -5.3871

Max Act: 2.7633. Min Act: -0.0000

Data Index: 1134971 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 5.3871. Min Range: -5.3871

Max Act: 2.8840. Min Act: -0.0000

Data Index: 127205 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 5.3871. Min Range: -5.3871

Max Act: 2.6060. Min Act: -0.0000

Data Index: 1132542 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 5.3871. Min Range: -5.3871

Max Act: 2.6698. Min Act: -0.0000

Data Index: 1035994 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 5.3871. Min Range: -5.3871

Max Act: 2.6302. Min Act: -0.0000

Data Index: 1196539 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 5.3871. Min Range: -5.3871

Max Act: 2.6971. Min Act: -0.0000

Data Index: 1264890 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 5.3871. Min Range: -5.3871

Max Act: 2.5405. Min Act: -0.0000

Data Index: 1038733 (C4 (Web Text))

Max Activating Token Index: 16