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

Dataset: The Pile

Neuron 3618 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: 0.8641. Min Range: -0.8641

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1760567 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.8018. Min Act: -0.0000

Data Index: 895173 (The Pile)

Max Activating Token Index: 133

Text #2

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1468489 (The Pile)

Max Activating Token Index: 391

Text #3

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.7276. Min Act: -0.0000

Data Index: 319413 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.7561. Min Act: -0.0000

Data Index: 416725 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6754. Min Act: -0.0000

Data Index: 563978 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6411. Min Act: -0.0000

Data Index: 418835 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6608. Min Act: -0.0000

Data Index: 223894 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1908242 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6217. Min Act: -0.0000

Data Index: 989627 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1033156 (The Pile)

Max Activating Token Index: 340

Text #11

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1440450 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6398. Min Act: -0.0000

Data Index: 117827 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6482. Min Act: -0.0000

Data Index: 161127 (The Pile)

Max Activating Token Index: 645

Text #14

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6484. Min Act: -0.0000

Data Index: 329714 (The Pile)

Max Activating Token Index: 45

Text #15

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6618. Min Act: -0.0000

Data Index: 387877 (The Pile)

Max Activating Token Index: 475

Text #16

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6017. Min Act: -0.0000

Data Index: 114590 (The Pile)

Max Activating Token Index: 702

Text #17

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6094. Min Act: -0.0000

Data Index: 261077 (The Pile)

Max Activating Token Index: 178

Text #18

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.5881. Min Act: -0.0000

Data Index: 168990 (The Pile)

Max Activating Token Index: 971

Text #19

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1229768 (The Pile)

Max Activating Token Index: 277