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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2826 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.4646. Min Act: -0.0000

Data Index: 655307 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.2357. Min Act: -0.0000

Data Index: 911322 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.2252. Min Act: -0.0000

Data Index: 1175433 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.1376. Min Act: -0.0000

Data Index: 1008568 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.1631. Min Act: -0.0000

Data Index: 73271 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0890. Min Act: -0.0000

Data Index: 578813 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1150134 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.1109. Min Act: -0.0000

Data Index: 129040 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0699. Min Act: -0.0000

Data Index: 128907 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0511. Min Act: -0.0000

Data Index: 409828 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0069. Min Act: -0.0000

Data Index: 839455 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1170988 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9064. Min Act: -0.0000

Data Index: 495087 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0578. Min Act: -0.0000

Data Index: 941908 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9082. Min Act: -0.0000

Data Index: 648308 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9231. Min Act: -0.0000

Data Index: 428307 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9117. Min Act: -0.0000

Data Index: 493604 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9020. Min Act: -0.0000

Data Index: 896978 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9207. Min Act: -0.0000

Data Index: 976306 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9261. Min Act: -0.0000

Data Index: 340436 (C4 (Web Text))

Max Activating Token Index: 400