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

Dataset: The Pile

Neuron 377 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: 0.8067. Min Range: -0.8067

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1128429 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.7793. Min Act: -0.0000

Data Index: 36234 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.7624. Min Act: -0.0000

Data Index: 775162 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6776. Min Act: -0.0000

Data Index: 516016 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1756125 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6844. Min Act: -0.0000

Data Index: 250245 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.7042. Min Act: -0.0000

Data Index: 439988 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.7531. Min Act: -0.0000

Data Index: 638462 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1622175 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1103374 (The Pile)

Max Activating Token Index: 633

Text #10

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1131427 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.7276. Min Act: -0.0000

Data Index: 710512 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6733. Min Act: -0.0000

Data Index: 869278 (The Pile)

Max Activating Token Index: 836

Text #13

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1770690 (The Pile)

Max Activating Token Index: 636

Text #14

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6849. Min Act: -0.0000

Data Index: 153326 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6588. Min Act: -0.0000

Data Index: 703704 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1116045 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.6415. Min Act: -0.0000

Data Index: 155162 (The Pile)

Max Activating Token Index: 192

Text #18

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5711. Min Act: -0.0000

Data Index: 67128 (The Pile)

Max Activating Token Index: 703

Text #19

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1150398 (The Pile)

Max Activating Token Index: 1023