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

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

Neuron 4945 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 146273 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 117751 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 888545 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 953092 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1324544 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1008811 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 43341 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 328203 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 911062 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 151418 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1239958 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1142563 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 858581 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 555993 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 373888 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 898499 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 210244 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1214652 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 110939 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 864782 (C4 (Web Text))

Max Activating Token Index: 473