Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 12 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.4743. Min Act: -0.0000

Data Index: 145029 (The Pile)

Max Activating Token Index: 149

Text #1

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.4831. Min Act: -0.0000

Data Index: 64152 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.1535. Min Act: -0.0000

Data Index: 1368777 (The Pile)

Max Activating Token Index: 589

Text #3

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.2976. Min Act: -0.0000

Data Index: 1194197 (The Pile)

Max Activating Token Index: 124

Text #4

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.2226. Min Act: -0.0000

Data Index: 839330 (The Pile)

Max Activating Token Index: 481

Text #5

Max Range: 3.4831. Min Range: -3.4831

Max Act: 2.7669. Min Act: -0.0000

Data Index: 494881 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.0368. Min Act: -0.0000

Data Index: 474775 (The Pile)

Max Activating Token Index: 567

Text #7

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.3296. Min Act: -0.0000

Data Index: 1228954 (The Pile)

Max Activating Token Index: 400

Text #8

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.1675. Min Act: -0.0000

Data Index: 1973549 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.1616. Min Act: -0.0000

Data Index: 1759298 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.0303. Min Act: -0.0000

Data Index: 406941 (The Pile)

Max Activating Token Index: 643

Text #11

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.1813. Min Act: -0.0000

Data Index: 1493984 (The Pile)

Max Activating Token Index: 666

Text #12

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.0112. Min Act: -0.0000

Data Index: 1859173 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.2968. Min Act: -0.0000

Data Index: 807211 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.1377. Min Act: -0.0000

Data Index: 1173807 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.3489. Min Act: -0.0000

Data Index: 1933893 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 3.4831. Min Range: -3.4831

Max Act: 2.6461. Min Act: -0.0000

Data Index: 952698 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.0450. Min Act: -0.0000

Data Index: 912190 (The Pile)

Max Activating Token Index: 799

Text #18

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.1693. Min Act: -0.0000

Data Index: 1673253 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 3.4831. Min Range: -3.4831

Max Act: 3.0273. Min Act: -0.0000

Data Index: 473133 (The Pile)

Max Activating Token Index: 523