Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2208 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.6656. Min Act: -0.0000

Data Index: 767149 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.9203. Min Act: -0.0000

Data Index: 1040733 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.9286. Min Act: -0.0000

Data Index: 1126380 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.8262. Min Act: -0.0000

Data Index: 879738 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.7399. Min Act: -0.0000

Data Index: 626371 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.5610. Min Act: -0.0000

Data Index: 917123 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.6757. Min Act: -0.0000

Data Index: 1316614 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.6214. Min Act: -0.0000

Data Index: 291816 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.3924. Min Act: -0.0000

Data Index: 309372 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.5022. Min Act: -0.0000

Data Index: 380061 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.4951. Min Act: -0.0000

Data Index: 1082614 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.4867. Min Act: -0.0000

Data Index: 231748 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.6485. Min Act: -0.0000

Data Index: 445221 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.6479. Min Act: -0.0000

Data Index: 918416 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.6321. Min Act: -0.0000

Data Index: 1181185 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.4663. Min Act: -0.0000

Data Index: 1031124 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.4217. Min Act: -0.0000

Data Index: 987492 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.4097. Min Act: -0.0000

Data Index: 228377 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.4157. Min Act: -0.0000

Data Index: 154004 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.1598. Min Act: -0.0000

Data Index: 991568 (C4 (Web Text))

Max Activating Token Index: 794