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

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

Neuron 699 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7538. Min Act: -0.0000

Data Index: 557354 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1170123 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.6268. Min Act: -0.0000

Data Index: 451874 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5838. Min Act: -0.0000

Data Index: 442073 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1265354 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5188. Min Act: -0.0000

Data Index: 26025 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5637. Min Act: -0.0000

Data Index: 715149 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5598. Min Act: -0.0000

Data Index: 846143 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5014. Min Act: -0.0000

Data Index: 273212 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5275. Min Act: -0.0000

Data Index: 660129 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1147476 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5137. Min Act: -0.0000

Data Index: 228299 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4837. Min Act: -0.0000

Data Index: 10769 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.5085. Min Act: -0.0000

Data Index: 860134 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4822. Min Act: -0.0000

Data Index: 443666 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4804. Min Act: -0.0000

Data Index: 694799 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1068339 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4715. Min Act: -0.0000

Data Index: 842459 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4840. Min Act: -0.0000

Data Index: 222585 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.7538. Min Range: -0.7538

Max Act: 0.4684. Min Act: -0.0000

Data Index: 526396 (C4 (Web Text))

Max Activating Token Index: 184