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

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

Neuron 1302 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8577. Min Act: -0.0000

Data Index: 450389 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.6021. Min Act: -0.0000

Data Index: 356335 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1137301 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.5466. Min Act: -0.0000

Data Index: 4376 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1145883 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1279118 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4756. Min Act: -0.0000

Data Index: 172521 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1032087 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4555. Min Act: -0.0000

Data Index: 445047 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4717. Min Act: -0.0000

Data Index: 802565 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1493109 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1180362 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1244727 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4796. Min Act: -0.0000

Data Index: 568599 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4887. Min Act: -0.0000

Data Index: 498761 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1477688 (Python Code)

Max Activating Token Index: 277

Text #16

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4717. Min Act: 0.0000

Data Index: 46614 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1494916 (Python Code)

Max Activating Token Index: 289

Text #18

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4197. Min Act: -0.0000

Data Index: 63736 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.4459. Min Act: -0.0000

Data Index: 664033 (C4 (Web Text))

Max Activating Token Index: 685