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

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

Neuron 1930 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7767. Min Range: -6.7767

Max Act: 6.7767. Min Act: -0.0000

Data Index: 420223 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 6.7767. Min Range: -6.7767

Max Act: 6.4721. Min Act: -0.0000

Data Index: 1287747 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 6.7767. Min Range: -6.7767

Max Act: 6.6492. Min Act: -0.0000

Data Index: 658911 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 6.7767. Min Range: -6.7767

Max Act: 6.4753. Min Act: -0.0000

Data Index: 1137766 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 6.7767. Min Range: -6.7767

Max Act: 6.2695. Min Act: -0.0000

Data Index: 15077 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 6.7767. Min Range: -6.7767

Max Act: 6.4298. Min Act: -0.0000

Data Index: 1181532 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 6.7767. Min Range: -6.7767

Max Act: 6.2012. Min Act: -0.0000

Data Index: 454726 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 6.7767. Min Range: -6.7767

Max Act: 6.3073. Min Act: -0.0000

Data Index: 180711 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 6.7767. Min Range: -6.7767

Max Act: 6.3948. Min Act: -0.0000

Data Index: 294803 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 6.7767. Min Range: -6.7767

Max Act: 5.8036. Min Act: -0.0000

Data Index: 1186488 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 6.7767. Min Range: -6.7767

Max Act: 5.8621. Min Act: -0.0000

Data Index: 201705 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 6.7767. Min Range: -6.7767

Max Act: 5.6201. Min Act: -0.0000

Data Index: 963430 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 6.7767. Min Range: -6.7767

Max Act: 5.8169. Min Act: -0.0000

Data Index: 1167934 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 6.7767. Min Range: -6.7767

Max Act: 5.9636. Min Act: -0.0000

Data Index: 417163 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 6.7767. Min Range: -6.7767

Max Act: 5.8061. Min Act: -0.0000

Data Index: 1352163 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 6.7767. Min Range: -6.7767

Max Act: 5.7494. Min Act: -0.0000

Data Index: 899953 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 6.7767. Min Range: -6.7767

Max Act: 5.5364. Min Act: -0.0000

Data Index: 1003345 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 6.7767. Min Range: -6.7767

Max Act: 5.7314. Min Act: -0.0000

Data Index: 325586 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 6.7767. Min Range: -6.7767

Max Act: 6.0679. Min Act: -0.0000

Data Index: 913209 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 6.7767. Min Range: -6.7767

Max Act: 5.5759. Min Act: -0.0000

Data Index: 619260 (C4 (Web Text))

Max Activating Token Index: 448