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

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

Neuron 944 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.2460. Min Act: -0.0000

Data Index: 317189 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1412. Min Act: -0.0000

Data Index: 800219 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.0512. Min Act: -0.0000

Data Index: 495764 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.0413. Min Act: -0.0000

Data Index: 392019 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.0046. Min Act: -0.0000

Data Index: 1393309 (Python Code)

Max Activating Token Index: 662

Text #5

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1399565 (Python Code)

Max Activating Token Index: 344

Text #6

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1471098 (Python Code)

Max Activating Token Index: 169

Text #7

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8883. Min Act: -0.0000

Data Index: 15821 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1493454 (Python Code)

Max Activating Token Index: 249

Text #9

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1629352 (Python Code)

Max Activating Token Index: 674

Text #10

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1440060 (Python Code)

Max Activating Token Index: 356

Text #11

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8935. Min Act: -0.0000

Data Index: 140453 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1514435 (Python Code)

Max Activating Token Index: 239

Text #13

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1418716 (Python Code)

Max Activating Token Index: 68

Text #14

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1493496 (Python Code)

Max Activating Token Index: 943

Text #15

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1402778 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8780. Min Act: -0.0000

Data Index: 801451 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1545019 (Python Code)

Max Activating Token Index: 161

Text #18

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8157. Min Act: -0.0000

Data Index: 1083944 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 1.2460. Min Range: -1.2460

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1500698 (Python Code)

Max Activating Token Index: 1009