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

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

Neuron 568 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2840. Min Range: -2.2840

Max Act: 2.2483. Min Act: 0.0000

Data Index: 226595 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 2.2840. Min Range: -2.2840

Max Act: 2.2840. Min Act: 0.0001

Data Index: 539348 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 2.2840. Min Range: -2.2840

Max Act: 2.0185. Min Act: -0.0000

Data Index: 20141 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.9840. Min Act: 0.0000

Data Index: 1212570 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.9162. Min Act: -0.0000

Data Index: 651760 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.7550. Min Act: -0.0000

Data Index: 1190811 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.9268. Min Act: 0.0000

Data Index: 1275252 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.8127. Min Act: -0.0000

Data Index: 84020 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.8732. Min Act: 0.0001

Data Index: 1266584 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.7877. Min Act: 0.0000

Data Index: 116165 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.7370. Min Act: -0.0000

Data Index: 333032 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.7085. Min Act: -0.0000

Data Index: 823051 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.6983. Min Act: -0.0000

Data Index: 832807 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.6610. Min Act: -0.0000

Data Index: 140138 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.6639. Min Act: 0.0000

Data Index: 328729 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.6640. Min Act: 0.0000

Data Index: 355480 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.6801. Min Act: -0.0000

Data Index: 359305 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.6543. Min Act: 0.0000

Data Index: 291829 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.6193. Min Act: 0.0001

Data Index: 960566 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 2.2840. Min Range: -2.2840

Max Act: 1.5756. Min Act: -0.0000

Data Index: 1088149 (C4 (Web Text))

Max Activating Token Index: 984