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

Dataset: The Pile

Neuron 724 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.6717. Min Act: -0.0000

Data Index: 961615 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1325213 (The Pile)

Max Activating Token Index: 371

Text #2

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5722. Min Act: -0.0000

Data Index: 723068 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1296927 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5417. Min Act: -0.0000

Data Index: 580343 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5282. Min Act: -0.0000

Data Index: 146990 (The Pile)

Max Activating Token Index: 963

Text #6

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4541. Min Act: -0.0000

Data Index: 920754 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4961. Min Act: 0.0001

Data Index: 134216 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4951. Min Act: -0.0000

Data Index: 763408 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1916219 (The Pile)

Max Activating Token Index: 24

Text #10

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4722. Min Act: -0.0000

Data Index: 888599 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4883. Min Act: -0.0000

Data Index: 957761 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1481035 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4543. Min Act: 0.0000

Data Index: 1150172 (The Pile)

Max Activating Token Index: 558

Text #14

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1285998 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4511. Min Act: -0.0000

Data Index: 483319 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4474. Min Act: -0.0000

Data Index: 375744 (The Pile)

Max Activating Token Index: 802

Text #17

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4533. Min Act: -0.0000

Data Index: 585879 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1084469 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1065948 (The Pile)

Max Activating Token Index: 687