Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3317 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1581. Min Act: -0.0000

Data Index: 610549 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1568. Min Act: -0.0000

Data Index: 616088 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1364810 (Python Code)

Max Activating Token Index: 474

Text #3

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1389. Min Act: -0.0000

Data Index: 630906 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1281. Min Act: -0.0001

Data Index: 291797 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1311. Min Act: -0.0000

Data Index: 608483 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1207. Min Act: -0.0001

Data Index: 449374 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1325. Min Act: -0.0001

Data Index: 384087 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1268. Min Act: -0.0001

Data Index: 497755 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1209. Min Act: -0.0001

Data Index: 318441 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1027. Min Act: -0.0001

Data Index: 796926 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1118. Min Act: -0.0000

Data Index: 66991 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1116. Min Act: -0.0000

Data Index: 330222 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1114. Min Act: -0.0001

Data Index: 40472 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1107. Min Act: -0.0001

Data Index: 832238 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1410380 (Python Code)

Max Activating Token Index: 149

Text #16

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0994. Min Act: -0.0000

Data Index: 184552 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1068. Min Act: -0.0000

Data Index: 986372 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1103. Min Act: -0.0000

Data Index: 692201 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1061. Min Act: -0.0001

Data Index: 393663 (C4 (Web Text))

Max Activating Token Index: 878