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

Dataset: The Pile

Neuron 2833 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: 1.7385. Min Range: -1.7385

Max Act: 1.6982. Min Act: -0.0000

Data Index: 1597921 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.6804. Min Act: -0.0000

Data Index: 545572 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.4834. Min Act: -0.0000

Data Index: 756735 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5645. Min Act: -0.0000

Data Index: 1769025 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.6581. Min Act: -0.0000

Data Index: 788202 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.7385. Min Act: -0.0000

Data Index: 521360 (The Pile)

Max Activating Token Index: 952

Text #6

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.7231. Min Act: -0.0000

Data Index: 1415856 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.6999. Min Act: -0.0000

Data Index: 949248 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.6024. Min Act: -0.0000

Data Index: 291891 (The Pile)

Max Activating Token Index: 1018

Text #9

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.4982. Min Act: -0.0000

Data Index: 1052817 (The Pile)

Max Activating Token Index: 832

Text #10

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5357. Min Act: -0.0000

Data Index: 1512515 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5411. Min Act: -0.0000

Data Index: 1400080 (The Pile)

Max Activating Token Index: 647

Text #12

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.4472. Min Act: -0.0000

Data Index: 1106739 (The Pile)

Max Activating Token Index: 235

Text #13

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5321. Min Act: -0.0000

Data Index: 779582 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.3570. Min Act: -0.0000

Data Index: 371455 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.4389. Min Act: -0.0000

Data Index: 1629960 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5078. Min Act: -0.0000

Data Index: 1325234 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5914. Min Act: -0.0000

Data Index: 489658 (The Pile)

Max Activating Token Index: 360

Text #18

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5077. Min Act: -0.0000

Data Index: 263954 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5870. Min Act: -0.0000

Data Index: 911447 (The Pile)

Max Activating Token Index: 883