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

Dataset: The Pile

Neuron 797 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1566860 (The Pile)

Max Activating Token Index: 64

Text #1

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5999. Min Act: -0.0000

Data Index: 989979 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5034. Min Act: -0.0000

Data Index: 464428 (The Pile)

Max Activating Token Index: 116

Text #3

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1448093 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1083366 (The Pile)

Max Activating Token Index: 346

Text #5

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1960833 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4183. Min Act: -0.0000

Data Index: 702624 (The Pile)

Max Activating Token Index: 302

Text #7

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4525. Min Act: -0.0000

Data Index: 529358 (The Pile)

Max Activating Token Index: 77

Text #8

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4094. Min Act: -0.0000

Data Index: 32157 (The Pile)

Max Activating Token Index: 602

Text #9

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3838. Min Act: -0.0000

Data Index: 978755 (The Pile)

Max Activating Token Index: 494

Text #10

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1601026 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4246. Min Act: -0.0000

Data Index: 923623 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4369. Min Act: -0.0000

Data Index: 298071 (The Pile)

Max Activating Token Index: 971

Text #13

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4342. Min Act: -0.0000

Data Index: 667837 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3793. Min Act: -0.0000

Data Index: 606676 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4285. Min Act: -0.0000

Data Index: 656991 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1617534 (The Pile)

Max Activating Token Index: 449

Text #17

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4261. Min Act: -0.0000

Data Index: 285951 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3576. Min Act: -0.0000

Data Index: 611400 (The Pile)

Max Activating Token Index: 1022

Text #19

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3861. Min Act: -0.0000

Data Index: 882702 (The Pile)

Max Activating Token Index: 191