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

Dataset: The Pile

Neuron 3576 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.2491. Min Act: -0.0000

Data Index: 951874 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1674. Min Act: -0.0000

Data Index: 1233463 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1749. Min Act: 0.0000

Data Index: 1131584 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1796. Min Act: -0.0000

Data Index: 331734 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1407. Min Act: -0.0000

Data Index: 715384 (The Pile)

Max Activating Token Index: 575

Text #5

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1618. Min Act: -0.0000

Data Index: 209970 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.0206. Min Act: -0.0000

Data Index: 873662 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1137. Min Act: -0.0000

Data Index: 1419926 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.0208. Min Act: -0.0000

Data Index: 48723 (The Pile)

Max Activating Token Index: 590

Text #9

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1207309 (The Pile)

Max Activating Token Index: 891

Text #10

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.0385. Min Act: -0.0000

Data Index: 1132289 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 1.2491. Min Range: -1.2491

Max Act: 0.9676. Min Act: -0.0000

Data Index: 698283 (The Pile)

Max Activating Token Index: 400

Text #12

Max Range: 1.2491. Min Range: -1.2491

Max Act: 0.9323. Min Act: -0.0000

Data Index: 403912 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 1.2491. Min Range: -1.2491

Max Act: 0.9520. Min Act: -0.0000

Data Index: 110045 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1408195 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 1.2491. Min Range: -1.2491

Max Act: 0.9413. Min Act: 0.0000

Data Index: 1432131 (The Pile)

Max Activating Token Index: 462

Text #16

Max Range: 1.2491. Min Range: -1.2491

Max Act: 0.9201. Min Act: -0.0000

Data Index: 944861 (The Pile)

Max Activating Token Index: 514

Text #17

Max Range: 1.2491. Min Range: -1.2491

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1853293 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 1.2491. Min Range: -1.2491

Max Act: 0.8607. Min Act: -0.0000

Data Index: 972134 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 1.2491. Min Range: -1.2491

Max Act: 0.9380. Min Act: -0.0000

Data Index: 718826 (The Pile)

Max Activating Token Index: 124