Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2491 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.8909. Min Act: -0.0001

Data Index: 1549271 (Python Code)

Max Activating Token Index: 659

Text #1

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1577618 (Python Code)

Max Activating Token Index: 590

Text #2

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7928. Min Act: -0.0001

Data Index: 1570885 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7934. Min Act: -0.0001

Data Index: 1490660 (Python Code)

Max Activating Token Index: 645

Text #4

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7859. Min Act: -0.0001

Data Index: 1476890 (Python Code)

Max Activating Token Index: 353

Text #5

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1516931 (Python Code)

Max Activating Token Index: 335

Text #6

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.8179. Min Act: -0.0001

Data Index: 1493502 (Python Code)

Max Activating Token Index: 738

Text #7

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1518815 (Python Code)

Max Activating Token Index: 40

Text #8

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7629. Min Act: -0.0001

Data Index: 1498108 (Python Code)

Max Activating Token Index: 508

Text #9

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7595. Min Act: -0.0001

Data Index: 1574105 (Python Code)

Max Activating Token Index: 480

Text #10

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1462011 (Python Code)

Max Activating Token Index: 579

Text #11

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7936. Min Act: -0.0001

Data Index: 1434820 (Python Code)

Max Activating Token Index: 64

Text #12

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1397017 (Python Code)

Max Activating Token Index: 127

Text #13

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7449. Min Act: -0.0001

Data Index: 1650971 (Python Code)

Max Activating Token Index: 738

Text #14

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.6878. Min Act: -0.0001

Data Index: 1427032 (Python Code)

Max Activating Token Index: 862

Text #15

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.6697. Min Act: -0.0001

Data Index: 1426312 (Python Code)

Max Activating Token Index: 235

Text #16

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1634209 (Python Code)

Max Activating Token Index: 456

Text #17

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7079. Min Act: -0.0001

Data Index: 1418354 (Python Code)

Max Activating Token Index: 179

Text #18

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1403058 (Python Code)

Max Activating Token Index: 256

Text #19

Max Range: 0.8909. Min Range: -0.8909

Max Act: 0.7221. Min Act: -0.0001

Data Index: 1535393 (Python Code)

Max Activating Token Index: 351