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

Dataset: The Pile

Neuron 4123 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.6104. Min Act: -0.0000

Data Index: 1250126 (The Pile)

Max Activating Token Index: 774

Text #1

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.3164. Min Act: -0.0000

Data Index: 704042 (The Pile)

Max Activating Token Index: 612

Text #2

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.3024. Min Act: -0.0000

Data Index: 1972586 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1907881 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.2531. Min Act: -0.0000

Data Index: 483248 (The Pile)

Max Activating Token Index: 440

Text #5

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1575761 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.0546. Min Act: -0.0000

Data Index: 539301 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.1141. Min Act: -0.0000

Data Index: 12719 (The Pile)

Max Activating Token Index: 918

Text #8

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.1059. Min Act: -0.0000

Data Index: 1473566 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9902. Min Act: -0.0000

Data Index: 589223 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1758949 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.0781. Min Act: -0.0000

Data Index: 1469216 (The Pile)

Max Activating Token Index: 394

Text #12

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9977. Min Act: -0.0000

Data Index: 779027 (The Pile)

Max Activating Token Index: 170

Text #13

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9903. Min Act: -0.0000

Data Index: 591214 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.0398. Min Act: -0.0000

Data Index: 928197 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.0308. Min Act: -0.0000

Data Index: 680576 (The Pile)

Max Activating Token Index: 61

Text #16

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9378. Min Act: -0.0000

Data Index: 936318 (The Pile)

Max Activating Token Index: 211

Text #17

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.0858. Min Act: -0.0000

Data Index: 712324 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9770. Min Act: -0.0000

Data Index: 757207 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1231273 (The Pile)

Max Activating Token Index: 524