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

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

Neuron 1517 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1364324 (Python Code)

Max Activating Token Index: 860

Text #1

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1516826 (Python Code)

Max Activating Token Index: 784

Text #2

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1590552 (Python Code)

Max Activating Token Index: 918

Text #3

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6782. Min Act: -0.0000

Data Index: 454507 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1535268 (Python Code)

Max Activating Token Index: 933

Text #5

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6350. Min Act: -0.0000

Data Index: 197182 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1442360 (Python Code)

Max Activating Token Index: 1016

Text #7

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6356. Min Act: -0.0000

Data Index: 960566 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5992. Min Act: -0.0000

Data Index: 1401460 (Python Code)

Max Activating Token Index: 941

Text #9

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1542246 (Python Code)

Max Activating Token Index: 894

Text #10

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1318999 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1398177 (Python Code)

Max Activating Token Index: 880

Text #12

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1557547 (Python Code)

Max Activating Token Index: 640

Text #13

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6217. Min Act: -0.0000

Data Index: 911071 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1500984 (Python Code)

Max Activating Token Index: 709

Text #15

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1009579 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1416909 (Python Code)

Max Activating Token Index: 906

Text #17

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1621954 (Python Code)

Max Activating Token Index: 267

Text #18

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5959. Min Act: -0.0000

Data Index: 609144 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.9117. Min Range: -0.9117

Max Act: 0.5806. Min Act: -0.0000

Data Index: 170317 (C4 (Web Text))

Max Activating Token Index: 243