Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1896 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.2047. Min Act: -0.0000

Data Index: 748245 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.6777. Min Act: -0.0000

Data Index: 1105930 (The Pile)

Max Activating Token Index: 242

Text #2

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.5240. Min Act: -0.0000

Data Index: 115668 (The Pile)

Max Activating Token Index: 916

Text #3

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.4064. Min Act: -0.0000

Data Index: 239165 (The Pile)

Max Activating Token Index: 522

Text #4

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.4461. Min Act: -0.0000

Data Index: 430744 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.3128. Min Act: -0.0000

Data Index: 1730646 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.4359. Min Act: -0.0000

Data Index: 1828213 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.2598. Min Act: -0.0000

Data Index: 1818582 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.0438. Min Act: -0.0000

Data Index: 238004 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.0256. Min Act: -0.0000

Data Index: 1722827 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.1139. Min Act: -0.0000

Data Index: 1045387 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.0555. Min Act: -0.0000

Data Index: 282048 (The Pile)

Max Activating Token Index: 742

Text #12

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.0296. Min Act: -0.0000

Data Index: 1580016 (The Pile)

Max Activating Token Index: 12

Text #13

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.0217. Min Act: -0.0000

Data Index: 1494394 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.0291. Min Act: -0.0000

Data Index: 182643 (The Pile)

Max Activating Token Index: 654

Text #15

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.0276. Min Act: -0.0000

Data Index: 178840 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 3.2047. Min Range: -3.2047

Max Act: 1.9837. Min Act: -0.0000

Data Index: 123745 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 3.2047. Min Range: -3.2047

Max Act: 1.8662. Min Act: -0.0000

Data Index: 839831 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 3.2047. Min Range: -3.2047

Max Act: 1.9467. Min Act: -0.0000

Data Index: 1894847 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 3.2047. Min Range: -3.2047

Max Act: 1.9580. Min Act: -0.0000

Data Index: 1837482 (The Pile)

Max Activating Token Index: 355