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

Dataset: The Pile

Neuron 684 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3146. Min Range: -1.3146

Max Act: 1.3146. Min Act: -0.0000

Data Index: 750769 (The Pile)

Max Activating Token Index: 847

Text #1

Max Range: 1.3146. Min Range: -1.3146

Max Act: 1.0583. Min Act: -0.0000

Data Index: 809403 (The Pile)

Max Activating Token Index: 889

Text #2

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.9509. Min Act: -0.0000

Data Index: 274721 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.8729. Min Act: -0.0000

Data Index: 95435 (The Pile)

Max Activating Token Index: 878

Text #4

Max Range: 1.3146. Min Range: -1.3146

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1276134 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.7678. Min Act: -0.0000

Data Index: 278575 (The Pile)

Max Activating Token Index: 669

Text #6

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1600382 (The Pile)

Max Activating Token Index: 777

Text #7

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.7573. Min Act: -0.0000

Data Index: 537097 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.7822. Min Act: -0.0000

Data Index: 260569 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1727128 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.8133. Min Act: -0.0000

Data Index: 1372033 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.7338. Min Act: -0.0000

Data Index: 264433 (The Pile)

Max Activating Token Index: 947

Text #12

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.8122. Min Act: -0.0000

Data Index: 775406 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1731936 (The Pile)

Max Activating Token Index: 457

Text #14

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1249824 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.7102. Min Act: -0.0000

Data Index: 246451 (The Pile)

Max Activating Token Index: 868

Text #16

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.7567. Min Act: -0.0000

Data Index: 472303 (The Pile)

Max Activating Token Index: 979

Text #17

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.7543. Min Act: 0.0000

Data Index: 725883 (The Pile)

Max Activating Token Index: 835

Text #18

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1047181 (The Pile)

Max Activating Token Index: 716

Text #19

Max Range: 1.3146. Min Range: -1.3146

Max Act: 0.6571. Min Act: -0.0000

Data Index: 222734 (The Pile)

Max Activating Token Index: 895