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

Dataset: The Pile

Neuron 3767 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: 0.8453. Min Range: -0.8453

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1262939 (The Pile)

Max Activating Token Index: 513

Text #1

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7368. Min Act: -0.0000

Data Index: 1450573 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1758222 (The Pile)

Max Activating Token Index: 195

Text #3

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6579. Min Act: -0.0000

Data Index: 320924 (The Pile)

Max Activating Token Index: 589

Text #4

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6620. Min Act: -0.0000

Data Index: 400023 (The Pile)

Max Activating Token Index: 204

Text #5

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7103. Min Act: -0.0000

Data Index: 960004 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6553. Min Act: -0.0000

Data Index: 820214 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6261. Min Act: -0.0000

Data Index: 340692 (The Pile)

Max Activating Token Index: 92

Text #8

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5845. Min Act: -0.0000

Data Index: 214730 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1196720 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6189. Min Act: -0.0000

Data Index: 66251 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6108. Min Act: -0.0000

Data Index: 336363 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6023. Min Act: -0.0000

Data Index: 633970 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1081958 (The Pile)

Max Activating Token Index: 910

Text #14

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6589. Min Act: -0.0000

Data Index: 842871 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5791. Min Act: -0.0000

Data Index: 321530 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5897. Min Act: -0.0000

Data Index: 491159 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6247. Min Act: -0.0000

Data Index: 471764 (The Pile)

Max Activating Token Index: 993

Text #18

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1354033 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6074. Min Act: -0.0000

Data Index: 555819 (The Pile)

Max Activating Token Index: 735