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

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

Neuron 3846 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: 1.5896. Min Range: -1.5896

Max Act: 1.5896. Min Act: -0.0000

Data Index: 307887 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.1800. Min Act: -0.0001

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2121. Min Act: -0.0000

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.8367. Min Act: -0.0000

Data Index: 42165 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.7692. Min Act: -0.0000

Data Index: 917327 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.7452. Min Act: -0.0000

Data Index: 278997 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.7264. Min Act: -0.0000

Data Index: 132892 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.7048. Min Act: -0.0000

Data Index: 263218 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1314882 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.7243. Min Act: -0.0000

Data Index: 226424 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1094708 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1318733 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.6817. Min Act: -0.0000

Data Index: 786760 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.6967. Min Act: -0.0000

Data Index: 146176 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.6955. Min Act: -0.0000

Data Index: 332955 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.6961. Min Act: -0.0000

Data Index: 551213 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.6656. Min Act: -0.0000

Data Index: 599785 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.7123. Min Act: -0.0000

Data Index: 146768 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.6405. Min Act: -0.0000

Data Index: 913102 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.7108. Min Act: -0.0000

Data Index: 827476 (C4 (Web Text))

Max Activating Token Index: 491