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

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

Neuron 5742 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.9062. Min Act: -0.0000

Data Index: 99929 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.8393. Min Act: -0.0000

Data Index: 35472 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.8653. Min Act: -0.0000

Data Index: 574399 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7760. Min Act: -0.0000

Data Index: 875879 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1085710 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7520. Min Act: -0.0000

Data Index: 791677 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7483. Min Act: -0.0000

Data Index: 601142 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1251338 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6676. Min Act: -0.0000

Data Index: 222395 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6934. Min Act: -0.0000

Data Index: 655538 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6719. Min Act: -0.0000

Data Index: 786826 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7468. Min Act: -0.0000

Data Index: 201053 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6756. Min Act: -0.0000

Data Index: 871136 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6925. Min Act: -0.0000

Data Index: 771548 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6331. Min Act: -0.0000

Data Index: 910206 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6271. Min Act: -0.0000

Data Index: 638130 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6376. Min Act: -0.0000

Data Index: 634846 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1269894 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.5768. Min Act: -0.0000

Data Index: 348394 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6465. Min Act: -0.0000

Data Index: 666518 (C4 (Web Text))

Max Activating Token Index: 500