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

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

Neuron 5004 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1212. Min Range: -1.1212

Max Act: 1.0957. Min Act: -0.0001

Data Index: 1416183 (Python Code)

Max Activating Token Index: 336

Text #1

Max Range: 1.1212. Min Range: -1.1212

Max Act: 1.1212. Min Act: -0.0001

Data Index: 1578617 (Python Code)

Max Activating Token Index: 790

Text #2

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.9547. Min Act: -0.0001

Data Index: 1407422 (Python Code)

Max Activating Token Index: 809

Text #3

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.9841. Min Act: -0.0001

Data Index: 998040 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8783. Min Act: -0.0001

Data Index: 1366735 (Python Code)

Max Activating Token Index: 801

Text #5

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8688. Min Act: -0.0001

Data Index: 1586083 (Python Code)

Max Activating Token Index: 845

Text #6

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.9763. Min Act: -0.0001

Data Index: 1481629 (Python Code)

Max Activating Token Index: 841

Text #7

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.9449. Min Act: -0.0001

Data Index: 1478922 (Python Code)

Max Activating Token Index: 800

Text #8

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.9032. Min Act: -0.0001

Data Index: 1597200 (Python Code)

Max Activating Token Index: 1007

Text #9

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.9381. Min Act: -0.0001

Data Index: 1608289 (Python Code)

Max Activating Token Index: 771

Text #10

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8657. Min Act: -0.0001

Data Index: 1533256 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8281. Min Act: -0.0001

Data Index: 1564229 (Python Code)

Max Activating Token Index: 632

Text #12

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.9034. Min Act: -0.0001

Data Index: 1611550 (Python Code)

Max Activating Token Index: 286

Text #13

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8684. Min Act: -0.0001

Data Index: 1493072 (Python Code)

Max Activating Token Index: 442

Text #14

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.9013. Min Act: -0.0001

Data Index: 1629356 (Python Code)

Max Activating Token Index: 313

Text #15

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8581. Min Act: -0.0001

Data Index: 818811 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8272. Min Act: -0.0001

Data Index: 1654973 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8453. Min Act: -0.0001

Data Index: 1483364 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8418. Min Act: -0.0001

Data Index: 1370804 (Python Code)

Max Activating Token Index: 435

Text #19

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8570. Min Act: -0.0001

Data Index: 756047 (C4 (Web Text))

Max Activating Token Index: 99