Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 276 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.5472. Min Act: -0.0000

Data Index: 1255474 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.5919. Min Act: -0.0000

Data Index: 266695 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.3829. Min Act: -0.0000

Data Index: 1664160 (The Pile)

Max Activating Token Index: 698

Text #3

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1899. Min Act: -0.0000

Data Index: 1566009 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1540. Min Act: -0.0000

Data Index: 1509884 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1112785 (The Pile)

Max Activating Token Index: 625

Text #6

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1739779 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2037. Min Act: -0.0000

Data Index: 296046 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1306. Min Act: -0.0000

Data Index: 261159 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1608. Min Act: -0.0000

Data Index: 742316 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1130. Min Act: -0.0000

Data Index: 1943103 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1471. Min Act: -0.0000

Data Index: 934712 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1461. Min Act: -0.0000

Data Index: 1050856 (The Pile)

Max Activating Token Index: 99

Text #13

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1466. Min Act: -0.0000

Data Index: 306671 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1065. Min Act: -0.0000

Data Index: 316108 (The Pile)

Max Activating Token Index: 45

Text #15

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1560954 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.0575. Min Act: -0.0000

Data Index: 1536673 (The Pile)

Max Activating Token Index: 771

Text #17

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1479. Min Act: -0.0000

Data Index: 1587347 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1018340 (The Pile)

Max Activating Token Index: 488

Text #19

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1122. Min Act: -0.0000

Data Index: 166964 (The Pile)

Max Activating Token Index: 774