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

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

Neuron 2654 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: 3.8717. Min Range: -3.8717

Max Act: 3.8717. Min Act: -0.0000

Data Index: 687381 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 3.8717. Min Range: -3.8717

Max Act: 3.3853. Min Act: -0.0000

Data Index: 1326933 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 3.8717. Min Range: -3.8717

Max Act: 3.4235. Min Act: -0.0000

Data Index: 210565 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 3.8717. Min Range: -3.8717

Max Act: 3.3513. Min Act: -0.0000

Data Index: 558236 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 3.8717. Min Range: -3.8717

Max Act: 3.3757. Min Act: -0.0000

Data Index: 1292046 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 3.8717. Min Range: -3.8717

Max Act: 3.1777. Min Act: -0.0000

Data Index: 112465 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.9569. Min Act: -0.0000

Data Index: 1086066 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.7942. Min Act: -0.0000

Data Index: 276642 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.7947. Min Act: -0.0000

Data Index: 1351253 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.6689. Min Act: -0.0000

Data Index: 744910 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.5171. Min Act: -0.0000

Data Index: 786264 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.5085. Min Act: -0.0000

Data Index: 651292 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.6104. Min Act: -0.0000

Data Index: 369199 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.6104. Min Act: -0.0000

Data Index: 625407 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.5723. Min Act: -0.0000

Data Index: 1327173 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.5466. Min Act: -0.0000

Data Index: 1236883 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.3725. Min Act: -0.0000

Data Index: 670443 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.3699. Min Act: -0.0000

Data Index: 942851 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.3157. Min Act: -0.0000

Data Index: 640219 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 3.8717. Min Range: -3.8717

Max Act: 2.4272. Min Act: -0.0000

Data Index: 1003720 (C4 (Web Text))

Max Activating Token Index: 853