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

Dataset: The Pile

Neuron 2685 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4698. Min Act: -0.0000

Data Index: 764123 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1832184 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3996. Min Act: -0.0000

Data Index: 297356 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1389677 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3505. Min Act: -0.0001

Data Index: 1198316 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3506. Min Act: -0.0000

Data Index: 988898 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3261. Min Act: -0.0000

Data Index: 205090 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3111. Min Act: -0.0000

Data Index: 747837 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3146. Min Act: -0.0001

Data Index: 540569 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3028. Min Act: -0.0001

Data Index: 1365569 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3103. Min Act: -0.0001

Data Index: 1485350 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3007. Min Act: -0.0001

Data Index: 914917 (The Pile)

Max Activating Token Index: 416

Text #12

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3178. Min Act: -0.0000

Data Index: 454807 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3038. Min Act: -0.0001

Data Index: 530567 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1019700 (The Pile)

Max Activating Token Index: 944

Text #15

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3020. Min Act: -0.0001

Data Index: 1463321 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.2980. Min Act: -0.0000

Data Index: 995004 (The Pile)

Max Activating Token Index: 620

Text #17

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.2993. Min Act: -0.0001

Data Index: 1988985 (The Pile)

Max Activating Token Index: 925

Text #18

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.2818. Min Act: -0.0001

Data Index: 1177818 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1231620 (The Pile)

Max Activating Token Index: 1007