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

Dataset: The Pile

Neuron 5078 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: 0.5415. Min Range: -0.5415

Max Act: 0.5415. Min Act: -0.0000

Data Index: 920042 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.5226. Min Act: 0.0000

Data Index: 1009 (The Pile)

Max Activating Token Index: 435

Text #2

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4978. Min Act: -0.0000

Data Index: 585124 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.5128. Min Act: -0.0000

Data Index: 505909 (The Pile)

Max Activating Token Index: 384

Text #4

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4430. Min Act: -0.0000

Data Index: 558550 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1074314 (The Pile)

Max Activating Token Index: 235

Text #6

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1100820 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1302673 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4282. Min Act: -0.0000

Data Index: 330692 (The Pile)

Max Activating Token Index: 483

Text #9

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4318. Min Act: -0.0000

Data Index: 882672 (The Pile)

Max Activating Token Index: 867

Text #10

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1688398 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1694653 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4316. Min Act: -0.0000

Data Index: 517675 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1946033 (The Pile)

Max Activating Token Index: 786

Text #14

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4068. Min Act: -0.0000

Data Index: 855640 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4187. Min Act: -0.0000

Data Index: 913251 (The Pile)

Max Activating Token Index: 999

Text #16

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1626577 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3794. Min Act: -0.0000

Data Index: 21691 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3775. Min Act: -0.0000

Data Index: 995934 (The Pile)

Max Activating Token Index: 337

Text #19

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.3764. Min Act: -0.0000

Data Index: 154671 (The Pile)

Max Activating Token Index: 102