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

Dataset: The Pile

Neuron 4144 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.2768. Min Act: -0.0000

Data Index: 1745616 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.2575. Min Act: -0.0000

Data Index: 322974 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.2314. Min Act: -0.0000

Data Index: 1352221 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1887485 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0806. Min Act: -0.0000

Data Index: 1829649 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1263487 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0333. Min Act: -0.0000

Data Index: 1922828 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.1929. Min Act: -0.0000

Data Index: 1420407 (The Pile)

Max Activating Token Index: 860

Text #8

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0575. Min Act: -0.0000

Data Index: 1602020 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0062. Min Act: -0.0000

Data Index: 855917 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9905. Min Act: -0.0000

Data Index: 80649 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1562190 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1258555 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1802638 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1683806 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0587. Min Act: -0.0000

Data Index: 268922 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0199. Min Act: -0.0000

Data Index: 145065 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9874. Min Act: -0.0000

Data Index: 288088 (The Pile)

Max Activating Token Index: 483

Text #18

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9878. Min Act: -0.0000

Data Index: 1303453 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1189936 (The Pile)

Max Activating Token Index: 71