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

Dataset: The Pile

Neuron 3356 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: 0.5050. Min Range: -0.5050

Max Act: 0.5050. Min Act: -0.0000

Data Index: 567730 (The Pile)

Max Activating Token Index: 709

Text #1

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4830. Min Act: -0.0000

Data Index: 500142 (The Pile)

Max Activating Token Index: 945

Text #2

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1730073 (The Pile)

Max Activating Token Index: 508

Text #3

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4307. Min Act: -0.0000

Data Index: 858686 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1254205 (The Pile)

Max Activating Token Index: 149

Text #5

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1804063 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3673. Min Act: -0.0000

Data Index: 426903 (The Pile)

Max Activating Token Index: 638

Text #7

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3332. Min Act: -0.0000

Data Index: 461138 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1377535 (The Pile)

Max Activating Token Index: 946

Text #9

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3341. Min Act: -0.0000

Data Index: 196671 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3237. Min Act: -0.0000

Data Index: 810831 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1521426 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3153. Min Act: -0.0000

Data Index: 774744 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1644675 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1810368 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3220. Min Act: -0.0000

Data Index: 997590 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1422664 (The Pile)

Max Activating Token Index: 562

Text #17

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1454166 (The Pile)

Max Activating Token Index: 604

Text #18

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1405788 (The Pile)

Max Activating Token Index: 650

Text #19

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2846. Min Act: -0.0000

Data Index: 673129 (The Pile)

Max Activating Token Index: 46