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

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

Neuron 2935 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: 1.0356. Min Range: -1.0356

Max Act: 1.0356. Min Act: -0.0001

Data Index: 619615 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.9364. Min Act: -0.0001

Data Index: 850571 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8674. Min Act: -0.0001

Data Index: 1608612 (Python Code)

Max Activating Token Index: 639

Text #3

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8891. Min Act: -0.0001

Data Index: 481086 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8641. Min Act: -0.0001

Data Index: 358796 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8605. Min Act: -0.0001

Data Index: 1378239 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8150. Min Act: -0.0001

Data Index: 602024 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8705. Min Act: -0.0001

Data Index: 1509919 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8826. Min Act: -0.0001

Data Index: 427602 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8754. Min Act: -0.0001

Data Index: 75605 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8091. Min Act: -0.0001

Data Index: 1641086 (Python Code)

Max Activating Token Index: 817

Text #11

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8163. Min Act: -0.0001

Data Index: 738659 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8122. Min Act: -0.0001

Data Index: 1279119 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.7803. Min Act: -0.0001

Data Index: 1430071 (Python Code)

Max Activating Token Index: 190

Text #14

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.7884. Min Act: -0.0001

Data Index: 1536192 (Python Code)

Max Activating Token Index: 319

Text #15

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8091. Min Act: -0.0001

Data Index: 1629672 (Python Code)

Max Activating Token Index: 305

Text #16

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.7786. Min Act: -0.0001

Data Index: 1549419 (Python Code)

Max Activating Token Index: 473

Text #17

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.7568. Min Act: -0.0001

Data Index: 1548414 (Python Code)

Max Activating Token Index: 462

Text #18

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.8002. Min Act: -0.0001

Data Index: 1133673 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 1.0356. Min Range: -1.0356

Max Act: 0.7686. Min Act: -0.0001

Data Index: 1627690 (Python Code)

Max Activating Token Index: 834