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

Dataset: The Pile

Neuron 1359 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: 1.5420. Min Range: -1.5420

Max Act: 1.3823. Min Act: -0.0000

Data Index: 1654615 (The Pile)

Max Activating Token Index: 762

Text #1

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.5420. Min Act: -0.0000

Data Index: 106917 (The Pile)

Max Activating Token Index: 445

Text #2

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.3525. Min Act: -0.0000

Data Index: 1942669 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.5309. Min Act: -0.0000

Data Index: 1302707 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.7135. Min Act: -0.0000

Data Index: 839721 (The Pile)

Max Activating Token Index: 821

Text #5

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.9146. Min Act: -0.0000

Data Index: 802184 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1968306 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.8432. Min Act: -0.0000

Data Index: 75176 (The Pile)

Max Activating Token Index: 922

Text #8

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.8163. Min Act: -0.0000

Data Index: 272815 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.8146. Min Act: -0.0000

Data Index: 304543 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1521061 (The Pile)

Max Activating Token Index: 596

Text #11

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1833465 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1909664 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1826504 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.7181. Min Act: -0.0000

Data Index: 444539 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1714399 (The Pile)

Max Activating Token Index: 209

Text #16

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1216343 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1280180 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1652929 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1604461 (The Pile)

Max Activating Token Index: 523