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

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

Neuron 959 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: 0.9508. Min Range: -0.9508

Max Act: 0.9508. Min Act: -0.0000

Data Index: 780145 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1257556 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7114. Min Act: -0.0000

Data Index: 502134 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6041. Min Act: -0.0000

Data Index: 938235 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1181164 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.5793. Min Act: -0.0000

Data Index: 209009 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.5396. Min Act: -0.0000

Data Index: 265520 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1335984 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.5171. Min Act: -0.0000

Data Index: 896935 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.5501. Min Act: -0.0000

Data Index: 301043 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.4934. Min Act: -0.0000

Data Index: 957802 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.5372. Min Act: 0.0000

Data Index: 1218692 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.4865. Min Act: -0.0000

Data Index: 707295 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.4927. Min Act: -0.0000

Data Index: 155707 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.4878. Min Act: -0.0000

Data Index: 885216 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1266946 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.4979. Min Act: -0.0000

Data Index: 326932 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.4566. Min Act: -0.0000

Data Index: 956864 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.4645. Min Act: -0.0000

Data Index: 989547 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.4619. Min Act: -0.0000

Data Index: 884949 (C4 (Web Text))

Max Activating Token Index: 70