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

Dataset: The Pile

Neuron 680 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.6093. Min Act: -0.0000

Data Index: 1312739 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.4186. Min Act: -0.0000

Data Index: 1212889 (The Pile)

Max Activating Token Index: 936

Text #2

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.9271. Min Act: -0.0000

Data Index: 1430285 (The Pile)

Max Activating Token Index: 800

Text #3

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.1887. Min Act: -0.0000

Data Index: 1479418 (The Pile)

Max Activating Token Index: 994

Text #4

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.1638. Min Act: -0.0000

Data Index: 793184 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.1884. Min Act: -0.0000

Data Index: 275559 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.9433. Min Act: -0.0000

Data Index: 173118 (The Pile)

Max Activating Token Index: 909

Text #7

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.8644. Min Act: -0.0000

Data Index: 1895707 (The Pile)

Max Activating Token Index: 509

Text #8

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.8099. Min Act: -0.0000

Data Index: 482942 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.7699. Min Act: -0.0000

Data Index: 1075580 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.7615. Min Act: -0.0000

Data Index: 587056 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.7119. Min Act: -0.0000

Data Index: 589217 (The Pile)

Max Activating Token Index: 788

Text #12

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.6699. Min Act: -0.0000

Data Index: 1502256 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.6350. Min Act: -0.0000

Data Index: 1362873 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.7731. Min Act: -0.0000

Data Index: 377127 (The Pile)

Max Activating Token Index: 48

Text #15

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.7430. Min Act: -0.0000

Data Index: 418852 (The Pile)

Max Activating Token Index: 512

Text #16

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.4737. Min Act: -0.0000

Data Index: 1630733 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.5771. Min Act: -0.0000

Data Index: 1430149 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.6766. Min Act: -0.0000

Data Index: 807426 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 3.6093. Min Range: -3.6093

Max Act: 2.5506. Min Act: -0.0000

Data Index: 360460 (The Pile)

Max Activating Token Index: 369