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

Dataset: The Pile

Neuron 2616 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: 0.8757. Min Range: -0.8757

Max Act: 0.7921. Min Act: -0.0000

Data Index: 879841 (The Pile)

Max Activating Token Index: 82

Text #1

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1896533 (The Pile)

Max Activating Token Index: 181

Text #2

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1230248 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7899. Min Act: -0.0000

Data Index: 205147 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1169121 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.8205. Min Act: -0.0000

Data Index: 1620112 (The Pile)

Max Activating Token Index: 793

Text #6

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1291747 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1591049 (The Pile)

Max Activating Token Index: 626

Text #8

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.8604. Min Act: -0.0000

Data Index: 83212 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1297042 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7543. Min Act: -0.0000

Data Index: 670762 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7285. Min Act: -0.0000

Data Index: 899506 (The Pile)

Max Activating Token Index: 6

Text #12

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1462194 (The Pile)

Max Activating Token Index: 358

Text #13

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1990626 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1243507 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7327. Min Act: -0.0000

Data Index: 817377 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1152600 (The Pile)

Max Activating Token Index: 750

Text #17

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7091. Min Act: -0.0000

Data Index: 342305 (The Pile)

Max Activating Token Index: 5

Text #18

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7435. Min Act: -0.0000

Data Index: 384524 (The Pile)

Max Activating Token Index: 851

Text #19

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.7423. Min Act: -0.0000

Data Index: 691749 (The Pile)

Max Activating Token Index: 554