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

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

Neuron 5042 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.9993. Min Act: -0.0001

Data Index: 1274918 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.9567. Min Act: -0.0001

Data Index: 867660 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.7268. Min Act: -0.0001

Data Index: 1034871 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.7940. Min Act: -0.0001

Data Index: 154247 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.8117. Min Act: -0.0001

Data Index: 936887 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.8753. Min Act: -0.0001

Data Index: 1352661 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.6160. Min Act: -0.0001

Data Index: 1207623 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.6983. Min Act: -0.0001

Data Index: 518530 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.6910. Min Act: -0.0001

Data Index: 957607 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.5595. Min Act: -0.0001

Data Index: 1195357 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.5396. Min Act: -0.0001

Data Index: 1324576 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.6975. Min Act: -0.0001

Data Index: 997808 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.6324. Min Act: -0.0001

Data Index: 879773 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.5677. Min Act: -0.0001

Data Index: 1090593 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.5670. Min Act: -0.0001

Data Index: 572845 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.4898. Min Act: -0.0001

Data Index: 647477 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.4586. Min Act: -0.0001

Data Index: 1110793 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.4899. Min Act: -0.0001

Data Index: 446967 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.4876. Min Act: -0.0001

Data Index: 956621 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.5161. Min Act: -0.0001

Data Index: 737792 (C4 (Web Text))

Max Activating Token Index: 144