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

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

Neuron 189 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: 0.4667. Min Range: -0.4667

Max Act: 0.4445. Min Act: -0.0000

Data Index: 803093 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1279178 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1040866 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4650. Min Act: -0.0000

Data Index: 238867 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4667. Min Act: -0.0000

Data Index: 504670 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3957. Min Act: -0.0000

Data Index: 532484 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4150. Min Act: -0.0000

Data Index: 444612 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4056. Min Act: -0.0000

Data Index: 139142 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4609. Min Act: -0.0000

Data Index: 355552 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4431. Min Act: -0.0000

Data Index: 126708 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4120. Min Act: -0.0000

Data Index: 849397 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1294031 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4204. Min Act: -0.0000

Data Index: 595300 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4482. Min Act: -0.0000

Data Index: 208750 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4138. Min Act: -0.0000

Data Index: 115713 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4424. Min Act: -0.0000

Data Index: 591931 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4256. Min Act: -0.0000

Data Index: 335142 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1009652 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4230. Min Act: -0.0000

Data Index: 702191 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4074. Min Act: -0.0000

Data Index: 459427 (C4 (Web Text))

Max Activating Token Index: 269