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

Dataset: The Pile

Neuron 3900 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.5812. Min Act: -0.0000

Data Index: 540677 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4988. Min Act: -0.0000

Data Index: 769338 (The Pile)

Max Activating Token Index: 761

Text #2

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1737825 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1262581 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4988. Min Act: -0.0000

Data Index: 173746 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1615999 (The Pile)

Max Activating Token Index: 256

Text #6

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1371785 (The Pile)

Max Activating Token Index: 580

Text #7

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1942640 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1383590 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1999147 (The Pile)

Max Activating Token Index: 113

Text #10

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1682884 (The Pile)

Max Activating Token Index: 972

Text #11

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1313602 (The Pile)

Max Activating Token Index: 537

Text #12

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1096417 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4131. Min Act: -0.0000

Data Index: 702878 (The Pile)

Max Activating Token Index: 655

Text #14

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1332961 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4188. Min Act: 0.0000

Data Index: 1006700 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4393. Min Act: -0.0000

Data Index: 827357 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4320. Min Act: -0.0000

Data Index: 538058 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1151414 (The Pile)

Max Activating Token Index: 884

Text #19

Max Range: 0.5812. Min Range: -0.5812

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1154662 (The Pile)

Max Activating Token Index: 316