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

Dataset: The Pile

Neuron 168 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: 0.8263. Min Range: -0.8263

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1716150 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1346806 (The Pile)

Max Activating Token Index: 134

Text #2

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7041. Min Act: -0.0000

Data Index: 594302 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7206. Min Act: -0.0000

Data Index: 881044 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6780. Min Act: -0.0000

Data Index: 449622 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6596. Min Act: -0.0000

Data Index: 130404 (The Pile)

Max Activating Token Index: 411

Text #6

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6769. Min Act: -0.0000

Data Index: 396993 (The Pile)

Max Activating Token Index: 400

Text #7

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6938. Min Act: -0.0000

Data Index: 407237 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1645627 (The Pile)

Max Activating Token Index: 61

Text #9

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6556. Min Act: -0.0000

Data Index: 464467 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1075462 (The Pile)

Max Activating Token Index: 681

Text #11

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1763215 (The Pile)

Max Activating Token Index: 707

Text #12

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1106497 (The Pile)

Max Activating Token Index: 677

Text #13

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6050. Min Act: -0.0000

Data Index: 219896 (The Pile)

Max Activating Token Index: 170

Text #14

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1604619 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5812. Min Act: -0.0000

Data Index: 757684 (The Pile)

Max Activating Token Index: 423

Text #16

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1607366 (The Pile)

Max Activating Token Index: 308

Text #17

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1370618 (The Pile)

Max Activating Token Index: 611

Text #18

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1124006 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1890404 (The Pile)

Max Activating Token Index: 38