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

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

Neuron 3420 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1437873 (Python Code)

Max Activating Token Index: 101

Text #1

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8406. Min Act: -0.0000

Data Index: 920280 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1573550 (Python Code)

Max Activating Token Index: 652

Text #3

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1324937 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7868. Min Act: -0.0000

Data Index: 209341 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8575. Min Act: -0.0001

Data Index: 1612862 (Python Code)

Max Activating Token Index: 169

Text #6

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7403. Min Act: -0.0001

Data Index: 1574668 (Python Code)

Max Activating Token Index: 172

Text #7

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1562052 (Python Code)

Max Activating Token Index: 891

Text #8

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1623869 (Python Code)

Max Activating Token Index: 675

Text #9

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8103. Min Act: -0.0001

Data Index: 1423244 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1475133 (Python Code)

Max Activating Token Index: 842

Text #11

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7199. Min Act: -0.0001

Data Index: 1414023 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6924. Min Act: -0.0001

Data Index: 1498937 (Python Code)

Max Activating Token Index: 946

Text #13

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7327. Min Act: -0.0001

Data Index: 1581248 (Python Code)

Max Activating Token Index: 638

Text #14

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6714. Min Act: -0.0001

Data Index: 1508082 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1432431 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6966. Min Act: -0.0001

Data Index: 1583124 (Python Code)

Max Activating Token Index: 556

Text #17

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6978. Min Act: -0.0001

Data Index: 1563828 (Python Code)

Max Activating Token Index: 211

Text #18

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7849. Min Act: -0.0001

Data Index: 1380213 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1389987 (Python Code)

Max Activating Token Index: 1014