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

Dataset: The Pile

Neuron 4054 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: 4.9946. Min Range: -4.9946

Max Act: 4.9946. Min Act: -0.0000

Data Index: 756203 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 4.9946. Min Range: -4.9946

Max Act: 4.3791. Min Act: -0.0000

Data Index: 1877225 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 4.9946. Min Range: -4.9946

Max Act: 4.6737. Min Act: -0.0000

Data Index: 1225517 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 4.9946. Min Range: -4.9946

Max Act: 4.0491. Min Act: -0.0000

Data Index: 1893100 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 4.9946. Min Range: -4.9946

Max Act: 4.3293. Min Act: -0.0000

Data Index: 26788 (The Pile)

Max Activating Token Index: 655

Text #5

Max Range: 4.9946. Min Range: -4.9946

Max Act: 4.2508. Min Act: -0.0000

Data Index: 1482378 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.9729. Min Act: -0.0000

Data Index: 386251 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.2115. Min Act: -0.0000

Data Index: 1337919 (The Pile)

Max Activating Token Index: 133

Text #8

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.9447. Min Act: -0.0000

Data Index: 943445 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.9294. Min Act: -0.0000

Data Index: 1023593 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.2016. Min Act: -0.0000

Data Index: 1346528 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.2806. Min Act: -0.0000

Data Index: 1469072 (The Pile)

Max Activating Token Index: 854

Text #12

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.3020. Min Act: -0.0000

Data Index: 505851 (The Pile)

Max Activating Token Index: 298

Text #13

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.2786. Min Act: -0.0000

Data Index: 317732 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.2538. Min Act: -0.0000

Data Index: 275685 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.1100. Min Act: -0.0000

Data Index: 1965576 (The Pile)

Max Activating Token Index: 916

Text #16

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.4010. Min Act: -0.0000

Data Index: 1054208 (The Pile)

Max Activating Token Index: 552

Text #17

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.4647. Min Act: -0.0000

Data Index: 1694726 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.4701. Min Act: -0.0000

Data Index: 1184669 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 4.9946. Min Range: -4.9946

Max Act: 3.2792. Min Act: -0.0000

Data Index: 1709213 (The Pile)

Max Activating Token Index: 48