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

Dataset: The Pile

Neuron 3487 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: 0.9452. Min Range: -0.9452

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1623464 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.9065. Min Act: -0.0000

Data Index: 316440 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1227966 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1361740 (The Pile)

Max Activating Token Index: 140

Text #4

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7020. Min Act: -0.0000

Data Index: 958429 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1855348 (The Pile)

Max Activating Token Index: 122

Text #6

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7776. Min Act: -0.0000

Data Index: 418430 (The Pile)

Max Activating Token Index: 372

Text #7

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.8070. Min Act: -0.0000

Data Index: 471679 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7624. Min Act: -0.0000

Data Index: 169146 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1026177 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1375607 (The Pile)

Max Activating Token Index: 533

Text #11

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7206. Min Act: -0.0000

Data Index: 273182 (The Pile)

Max Activating Token Index: 427

Text #12

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7856. Min Act: -0.0000

Data Index: 729299 (The Pile)

Max Activating Token Index: 16

Text #13

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6716. Min Act: -0.0000

Data Index: 590915 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1656183 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7603. Min Act: -0.0000

Data Index: 726797 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1638180 (The Pile)

Max Activating Token Index: 631

Text #17

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6769. Min Act: -0.0000

Data Index: 136587 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1723477 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1071937 (The Pile)

Max Activating Token Index: 223