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

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

Neuron 1829 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.3086. Min Act: -0.0001

Data Index: 1587696 (Python Code)

Max Activating Token Index: 563

Text #1

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.2863. Min Act: -0.0001

Data Index: 1379080 (Python Code)

Max Activating Token Index: 695

Text #2

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.2374. Min Act: -0.0001

Data Index: 187179 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.1424. Min Act: -0.0001

Data Index: 487402 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.1738. Min Act: -0.0001

Data Index: 41672 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0320. Min Act: -0.0001

Data Index: 561535 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0306. Min Act: -0.0001

Data Index: 1286069 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0458. Min Act: -0.0001

Data Index: 952812 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9792. Min Act: -0.0001

Data Index: 507220 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9151. Min Act: -0.0001

Data Index: 369811 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0597. Min Act: -0.0001

Data Index: 177190 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9515. Min Act: -0.0001

Data Index: 217695 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0337. Min Act: -0.0001

Data Index: 43504 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0733. Min Act: -0.0001

Data Index: 354772 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9850. Min Act: -0.0001

Data Index: 446519 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0057. Min Act: -0.0001

Data Index: 3598 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9435. Min Act: -0.0001

Data Index: 666541 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9845. Min Act: -0.0001

Data Index: 895994 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9845. Min Act: -0.0001

Data Index: 942939 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9845. Min Act: -0.0001

Data Index: 770193 (C4 (Web Text))

Max Activating Token Index: 2