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

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

Neuron 1055 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1224997 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.9081. Min Act: -0.0000

Data Index: 102377 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1178477 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.8261. Min Act: -0.0000

Data Index: 726505 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1119210 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7831. Min Act: -0.0000

Data Index: 750237 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.8260. Min Act: -0.0000

Data Index: 193636 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7786. Min Act: 0.0000

Data Index: 454692 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7239. Min Act: -0.0000

Data Index: 207830 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.6877. Min Act: -0.0000

Data Index: 763701 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.6369. Min Act: -0.0000

Data Index: 490142 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1044214 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1129847 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1301756 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1142488 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.6406. Min Act: -0.0000

Data Index: 58086 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.5850. Min Act: -0.0000

Data Index: 728036 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.6241. Min Act: -0.0000

Data Index: 670351 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1080954 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1331681 (C4 (Web Text))

Max Activating Token Index: 64