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

Dataset: The Pile

Neuron 3671 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1091. Min Act: -0.0000

Data Index: 414658 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1782. Min Act: -0.0000

Data Index: 394669 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1942908 (The Pile)

Max Activating Token Index: 190

Text #3

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0151. Min Act: -0.0001

Data Index: 1736712 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1057769 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1218178 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1122. Min Act: -0.0000

Data Index: 866684 (The Pile)

Max Activating Token Index: 506

Text #7

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1810160 (The Pile)

Max Activating Token Index: 430

Text #8

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0454. Min Act: -0.0001

Data Index: 586281 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1842531 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9471. Min Act: -0.0000

Data Index: 817768 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9137. Min Act: -0.0001

Data Index: 499732 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0687. Min Act: -0.0000

Data Index: 721907 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0866. Min Act: -0.0000

Data Index: 30912 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1773. Min Act: -0.0001

Data Index: 1108248 (The Pile)

Max Activating Token Index: 576

Text #15

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9321. Min Act: -0.0000

Data Index: 374834 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0514. Min Act: -0.0000

Data Index: 902110 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0363. Min Act: -0.0000

Data Index: 1420145 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9945. Min Act: -0.0000

Data Index: 764772 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0279. Min Act: -0.0000

Data Index: 1307149 (The Pile)

Max Activating Token Index: 536