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

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

Neuron 1571 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: 0.6523. Min Range: -0.6523

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1171914 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5956. Min Act: -0.0000

Data Index: 373260 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5420. Min Act: -0.0000

Data Index: 108391 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5354. Min Act: -0.0000

Data Index: 725225 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1027505 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5327. Min Act: -0.0000

Data Index: 418681 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5217. Min Act: -0.0000

Data Index: 22481 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5213. Min Act: -0.0000

Data Index: 844056 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1203267 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1095015 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.4949. Min Act: -0.0000

Data Index: 301545 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5286. Min Act: -0.0000

Data Index: 764132 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5184. Min Act: -0.0000

Data Index: 61296 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5014. Min Act: -0.0000

Data Index: 484117 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.4546. Min Act: -0.0000

Data Index: 960790 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5124. Min Act: -0.0000

Data Index: 753885 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5065. Min Act: -0.0000

Data Index: 143463 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.4991. Min Act: -0.0000

Data Index: 454087 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.4812. Min Act: -0.0000

Data Index: 367827 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.6523. Min Range: -0.6523

Max Act: 0.5032. Min Act: -0.0000

Data Index: 228949 (C4 (Web Text))

Max Activating Token Index: 179