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

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

Neuron 2449 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0765. Min Range: -1.0765

Max Act: 1.0765. Min Act: -0.0000

Data Index: 813568 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9953. Min Act: -0.0000

Data Index: 281081 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9858. Min Act: -0.0000

Data Index: 189197 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9827. Min Act: -0.0000

Data Index: 769822 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1069076 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1097971 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9571. Min Act: -0.0000

Data Index: 318937 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1247841 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9395. Min Act: -0.0000

Data Index: 964213 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1299312 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9329. Min Act: -0.0000

Data Index: 885571 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1085358 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1148335 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1297070 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.8977. Min Act: -0.0000

Data Index: 513000 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.8977. Min Act: -0.0000

Data Index: 990503 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1286366 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.8888. Min Act: -0.0000

Data Index: 417712 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1085908 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1160419 (C4 (Web Text))

Max Activating Token Index: 522