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

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

Neuron 471 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3619. Min Range: -3.3619

Max Act: 3.3619. Min Act: -0.0000

Data Index: 353112 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 3.3619. Min Range: -3.3619

Max Act: 3.1736. Min Act: -0.0000

Data Index: 993127 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8593. Min Act: -0.0000

Data Index: 1616528 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.9576. Min Act: -0.0000

Data Index: 257886 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.9571. Min Act: -0.0000

Data Index: 1459774 (Python Code)

Max Activating Token Index: 612

Text #5

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.9118. Min Act: -0.0000

Data Index: 699050 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8808. Min Act: -0.0000

Data Index: 1040212 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8803. Min Act: -0.0000

Data Index: 336236 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.7162. Min Act: -0.0000

Data Index: 1057729 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.9575. Min Act: -0.0000

Data Index: 1486921 (Python Code)

Max Activating Token Index: 119

Text #10

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.6474. Min Act: -0.0000

Data Index: 1378660 (Python Code)

Max Activating Token Index: 859

Text #11

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.6903. Min Act: -0.0000

Data Index: 1161758 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.4937. Min Act: -0.0000

Data Index: 826052 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.7854. Min Act: -0.0000

Data Index: 1509557 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.6457. Min Act: -0.0000

Data Index: 1517522 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.5009. Min Act: -0.0000

Data Index: 1588240 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.7612. Min Act: -0.0000

Data Index: 686994 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.3299. Min Act: -0.0000

Data Index: 514503 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.4500. Min Act: -0.0000

Data Index: 1198223 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.4857. Min Act: -0.0000

Data Index: 1307202 (C4 (Web Text))

Max Activating Token Index: 249