Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2274 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5731. Min Act: -0.0001

Data Index: 468790 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5764. Min Act: -0.0001

Data Index: 1955729 (The Pile)

Max Activating Token Index: 166

Text #2

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5453. Min Act: -0.0000

Data Index: 576804 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5242. Min Act: -0.0001

Data Index: 1088552 (The Pile)

Max Activating Token Index: 124

Text #4

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5054. Min Act: -0.0001

Data Index: 322163 (The Pile)

Max Activating Token Index: 663

Text #5

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5429. Min Act: -0.0001

Data Index: 835541 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1364924 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5111. Min Act: -0.0001

Data Index: 192835 (The Pile)

Max Activating Token Index: 979

Text #8

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4895. Min Act: -0.0000

Data Index: 252066 (The Pile)

Max Activating Token Index: 567

Text #9

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5004. Min Act: -0.0000

Data Index: 339648 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4788. Min Act: -0.0001

Data Index: 715193 (The Pile)

Max Activating Token Index: 261

Text #11

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4893. Min Act: -0.0001

Data Index: 308975 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4958. Min Act: -0.0000

Data Index: 784965 (The Pile)

Max Activating Token Index: 821

Text #13

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5112. Min Act: -0.0000

Data Index: 803518 (The Pile)

Max Activating Token Index: 53

Text #14

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4670. Min Act: -0.0000

Data Index: 771242 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4654. Min Act: -0.0000

Data Index: 521069 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4611. Min Act: -0.0001

Data Index: 374989 (The Pile)

Max Activating Token Index: 942

Text #17

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4774. Min Act: -0.0001

Data Index: 1873588 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1618692 (The Pile)

Max Activating Token Index: 585

Text #19

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4546. Min Act: -0.0000

Data Index: 572922 (The Pile)

Max Activating Token Index: 879