Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4597 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7937. Min Act: -0.0001

Data Index: 1474937 (Python Code)

Max Activating Token Index: 933

Text #1

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7798. Min Act: -0.0001

Data Index: 1419691 (Python Code)

Max Activating Token Index: 161

Text #2

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7013. Min Act: -0.0001

Data Index: 1422958 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7600. Min Act: -0.0001

Data Index: 1532201 (Python Code)

Max Activating Token Index: 411

Text #4

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7510. Min Act: -0.0001

Data Index: 1469120 (Python Code)

Max Activating Token Index: 503

Text #5

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7184. Min Act: -0.0001

Data Index: 1610285 (Python Code)

Max Activating Token Index: 400

Text #6

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7463. Min Act: -0.0001

Data Index: 1637211 (Python Code)

Max Activating Token Index: 956

Text #7

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7341. Min Act: -0.0001

Data Index: 1637075 (Python Code)

Max Activating Token Index: 98

Text #8

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7878. Min Act: -0.0001

Data Index: 1586230 (Python Code)

Max Activating Token Index: 941

Text #9

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7219. Min Act: -0.0001

Data Index: 1486313 (Python Code)

Max Activating Token Index: 156

Text #10

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7386. Min Act: -0.0001

Data Index: 1487079 (Python Code)

Max Activating Token Index: 937

Text #11

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6098. Min Act: -0.0001

Data Index: 1400393 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6695. Min Act: -0.0001

Data Index: 1373544 (Python Code)

Max Activating Token Index: 646

Text #13

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7055. Min Act: -0.0001

Data Index: 1484561 (Python Code)

Max Activating Token Index: 491

Text #14

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7210. Min Act: -0.0001

Data Index: 1440163 (Python Code)

Max Activating Token Index: 251

Text #15

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6437. Min Act: -0.0001

Data Index: 1464359 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.7114. Min Act: -0.0001

Data Index: 1602423 (Python Code)

Max Activating Token Index: 995

Text #17

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6697. Min Act: -0.0001

Data Index: 1438391 (Python Code)

Max Activating Token Index: 74

Text #18

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6635. Min Act: -0.0001

Data Index: 1492841 (Python Code)

Max Activating Token Index: 261

Text #19

Max Range: 0.7937. Min Range: -0.7937

Max Act: 0.6488. Min Act: -0.0001

Data Index: 1616344 (Python Code)

Max Activating Token Index: 266