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

Dataset: The Pile

Neuron 4053 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0038. Min Range: -1.0038

Max Act: 1.0038. Min Act: -0.0000

Data Index: 139641 (The Pile)

Max Activating Token Index: 693

Text #1

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1743024 (The Pile)

Max Activating Token Index: 712

Text #2

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1053610 (The Pile)

Max Activating Token Index: 548

Text #3

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7982. Min Act: -0.0000

Data Index: 581864 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1810535 (The Pile)

Max Activating Token Index: 341

Text #5

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1572396 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7903. Min Act: -0.0000

Data Index: 910294 (The Pile)

Max Activating Token Index: 827

Text #7

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.8264. Min Act: -0.0000

Data Index: 915416 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1097417 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1782885 (The Pile)

Max Activating Token Index: 901

Text #10

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1550018 (The Pile)

Max Activating Token Index: 502

Text #11

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7296. Min Act: -0.0000

Data Index: 785540 (The Pile)

Max Activating Token Index: 659

Text #12

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7978. Min Act: -0.0000

Data Index: 97735 (The Pile)

Max Activating Token Index: 373

Text #13

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1880163 (The Pile)

Max Activating Token Index: 371

Text #14

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1197862 (The Pile)

Max Activating Token Index: 390

Text #15

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1015434 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1971734 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1355606 (The Pile)

Max Activating Token Index: 241

Text #18

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7650. Min Act: -0.0000

Data Index: 57569 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1029092 (The Pile)

Max Activating Token Index: 94