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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3504 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0257. Min Act: -0.0002

Data Index: 502247 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1312020 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1087248 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1103188 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0108. Min Act: -0.0002

Data Index: 546463 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0108. Min Act: -0.0002

Data Index: 830995 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1157241 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0103. Min Act: -0.0002

Data Index: 905344 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1256826 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1295091 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0110. Min Act: -0.0002

Data Index: 396254 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0105. Min Act: -0.0002

Data Index: 69781 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0103. Min Act: -0.0002

Data Index: 771377 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0103. Min Act: -0.0002

Data Index: 683799 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0100. Min Act: -0.0002

Data Index: 528919 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1110947 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1348698 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0101. Min Act: -0.0002

Data Index: 987659 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0084. Min Act: -0.0002

Data Index: 955733 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1183845 (C4 (Web Text))

Max Activating Token Index: 310