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

Dataset: The Pile

Neuron 3572 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.2542. Min Act: -0.0000

Data Index: 918780 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0416. Min Act: -0.0000

Data Index: 37965 (The Pile)

Max Activating Token Index: 10

Text #2

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0946. Min Act: -0.0000

Data Index: 1065221 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0184. Min Act: -0.0000

Data Index: 253556 (The Pile)

Max Activating Token Index: 610

Text #4

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0082. Min Act: -0.0000

Data Index: 411823 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1559180 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.9345. Min Act: -0.0000

Data Index: 779736 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.8090. Min Act: -0.0000

Data Index: 306685 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.9095. Min Act: -0.0000

Data Index: 433405 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1259592 (The Pile)

Max Activating Token Index: 857

Text #10

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.8317. Min Act: -0.0000

Data Index: 614236 (The Pile)

Max Activating Token Index: 678

Text #11

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.8609. Min Act: -0.0000

Data Index: 244202 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1153781 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1157323 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1446273 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.8193. Min Act: -0.0000

Data Index: 104579 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1663258 (The Pile)

Max Activating Token Index: 188

Text #17

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.7032. Min Act: -0.0000

Data Index: 754501 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.8666. Min Act: -0.0000

Data Index: 117136 (The Pile)

Max Activating Token Index: 951

Text #19

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.8012. Min Act: -0.0000

Data Index: 416474 (The Pile)

Max Activating Token Index: 376