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

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

Neuron 1124 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.5596. Min Act: -0.0000

Data Index: 118652 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4985. Min Act: -0.0000

Data Index: 353203 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4952. Min Act: -0.0000

Data Index: 339677 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1206288 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4669. Min Act: -0.0000

Data Index: 772609 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3890. Min Act: -0.0000

Data Index: 886234 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1168279 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3119. Min Act: -0.0000

Data Index: 383250 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3320. Min Act: -0.0000

Data Index: 410707 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1597553 (Python Code)

Max Activating Token Index: 523

Text #10

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1514721 (Python Code)

Max Activating Token Index: 163

Text #11

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.2911. Min Act: -0.0000

Data Index: 610946 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3166. Min Act: -0.0000

Data Index: 74855 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3231. Min Act: -0.0000

Data Index: 544756 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3061. Min Act: -0.0000

Data Index: 784242 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3069. Min Act: -0.0000

Data Index: 992538 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1557149 (Python Code)

Max Activating Token Index: 673

Text #17

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.2828. Min Act: -0.0000

Data Index: 668300 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3005. Min Act: -0.0000

Data Index: 503755 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.2904. Min Act: -0.0000

Data Index: 989681 (C4 (Web Text))

Max Activating Token Index: 942