Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2893 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1593. Min Act: -0.0001

Data Index: 606922 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1400. Min Act: -0.0001

Data Index: 1188350 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1268. Min Act: -0.0001

Data Index: 916629 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1236. Min Act: -0.0001

Data Index: 357223 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1245. Min Act: -0.0001

Data Index: 973668 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1114343 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0936. Min Act: -0.0001

Data Index: 512615 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1073. Min Act: -0.0001

Data Index: 741205 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1186. Min Act: -0.0001

Data Index: 542456 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1112. Min Act: -0.0001

Data Index: 682225 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1063. Min Act: -0.0001

Data Index: 325664 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1125. Min Act: -0.0001

Data Index: 376340 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1009. Min Act: -0.0001

Data Index: 150478 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1021. Min Act: -0.0001

Data Index: 115161 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1099197 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1031. Min Act: -0.0001

Data Index: 281550 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1025. Min Act: -0.0001

Data Index: 811718 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1039. Min Act: -0.0001

Data Index: 157868 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0979. Min Act: -0.0001

Data Index: 402792 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0966. Min Act: -0.0001

Data Index: 81892 (C4 (Web Text))

Max Activating Token Index: 924