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

Dataset: The Pile

Neuron 3113 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.6425. Min Act: -0.0000

Data Index: 37754 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.5987. Min Act: -0.0001

Data Index: 1688627 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.4885. Min Act: -0.0001

Data Index: 1909807 (The Pile)

Max Activating Token Index: 190

Text #3

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1116247 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.3872. Min Act: -0.0000

Data Index: 213870 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.6187. Min Act: -0.0000

Data Index: 875435 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.5182. Min Act: -0.0000

Data Index: 759968 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1542841 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.4732. Min Act: -0.0000

Data Index: 945354 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.4532. Min Act: -0.0000

Data Index: 1497176 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.3700. Min Act: -0.0000

Data Index: 1661393 (The Pile)

Max Activating Token Index: 534

Text #11

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.5324. Min Act: -0.0000

Data Index: 185548 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.5355. Min Act: -0.0000

Data Index: 1651514 (The Pile)

Max Activating Token Index: 632

Text #13

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.5057. Min Act: -0.0000

Data Index: 1680188 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.3598. Min Act: -0.0000

Data Index: 891341 (The Pile)

Max Activating Token Index: 1004

Text #15

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.4091. Min Act: -0.0000

Data Index: 1044182 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1681188 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.4066. Min Act: -0.0000

Data Index: 1834398 (The Pile)

Max Activating Token Index: 423

Text #18

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1832574 (The Pile)

Max Activating Token Index: 846

Text #19

Max Range: 1.6425. Min Range: -1.6425

Max Act: 1.3882. Min Act: -0.0000

Data Index: 430107 (The Pile)

Max Activating Token Index: 495