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

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

Neuron 2293 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7305. Min Range: -2.7305

Max Act: 2.7305. Min Act: -0.0000

Data Index: 1157763 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 2.7305. Min Range: -2.7305

Max Act: 2.6393. Min Act: -0.0000

Data Index: 170160 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 2.7305. Min Range: -2.7305

Max Act: 2.3555. Min Act: -0.0000

Data Index: 555722 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 2.7305. Min Range: -2.7305

Max Act: 2.2069. Min Act: -0.0000

Data Index: 1166623 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 2.7305. Min Range: -2.7305

Max Act: 2.1376. Min Act: -0.0000

Data Index: 613597 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 2.7305. Min Range: -2.7305

Max Act: 2.1251. Min Act: -0.0000

Data Index: 283212 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 2.7305. Min Range: -2.7305

Max Act: 2.1205. Min Act: -0.0000

Data Index: 879615 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 2.7305. Min Range: -2.7305

Max Act: 1.9885. Min Act: -0.0000

Data Index: 1140045 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 2.7305. Min Range: -2.7305

Max Act: 2.0380. Min Act: -0.0000

Data Index: 1181516 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 2.7305. Min Range: -2.7305

Max Act: 1.9816. Min Act: -0.0000

Data Index: 154871 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 2.7305. Min Range: -2.7305

Max Act: 1.9758. Min Act: -0.0000

Data Index: 522073 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 2.7305. Min Range: -2.7305

Max Act: 1.9441. Min Act: -0.0000

Data Index: 1307872 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 2.7305. Min Range: -2.7305

Max Act: 2.0478. Min Act: -0.0000

Data Index: 717303 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 2.7305. Min Range: -2.7305

Max Act: 1.9410. Min Act: -0.0000

Data Index: 1146601 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 2.7305. Min Range: -2.7305

Max Act: 1.9237. Min Act: -0.0000

Data Index: 667674 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 2.7305. Min Range: -2.7305

Max Act: 1.8040. Min Act: -0.0000

Data Index: 672156 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 2.7305. Min Range: -2.7305

Max Act: 1.8927. Min Act: -0.0000

Data Index: 670956 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 2.7305. Min Range: -2.7305

Max Act: 1.8829. Min Act: -0.0000

Data Index: 259586 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 2.7305. Min Range: -2.7305

Max Act: 1.8742. Min Act: -0.0000

Data Index: 825639 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 2.7305. Min Range: -2.7305

Max Act: 1.8695. Min Act: -0.0000

Data Index: 280598 (C4 (Web Text))

Max Activating Token Index: 229