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

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

Neuron 2881 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: 0.2942. Min Range: -0.2942

Max Act: 0.2942. Min Act: -0.0000

Data Index: 351914 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2497. Min Act: -0.0000

Data Index: 552301 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2403. Min Act: -0.0000

Data Index: 830416 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2358. Min Act: -0.0000

Data Index: 942281 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2248. Min Act: -0.0000

Data Index: 103795 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2294. Min Act: -0.0000

Data Index: 371294 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2196. Min Act: -0.0000

Data Index: 948867 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2275. Min Act: -0.0000

Data Index: 751736 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2277. Min Act: -0.0000

Data Index: 50056 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1342682 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2248. Min Act: -0.0000

Data Index: 752849 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2077. Min Act: -0.0000

Data Index: 427113 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2054. Min Act: -0.0000

Data Index: 638349 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2118. Min Act: -0.0000

Data Index: 687156 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2189. Min Act: -0.0000

Data Index: 995152 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2100. Min Act: -0.0000

Data Index: 883462 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2015. Min Act: -0.0000

Data Index: 965143 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2017. Min Act: -0.0000

Data Index: 297910 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2005. Min Act: -0.0000

Data Index: 409783 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2142. Min Act: -0.0000

Data Index: 297834 (C4 (Web Text))

Max Activating Token Index: 766