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

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

Neuron 2127 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1216786 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1035719 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3807. Min Act: -0.0001

Data Index: 952775 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3748. Min Act: -0.0000

Data Index: 37451 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3714. Min Act: -0.0000

Data Index: 81045 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3836. Min Act: -0.0000

Data Index: 381921 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3885. Min Act: -0.0000

Data Index: 1005476 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3538. Min Act: -0.0000

Data Index: 225388 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3385. Min Act: -0.0001

Data Index: 887535 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3339. Min Act: -0.0000

Data Index: 435520 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1155962 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3070. Min Act: -0.0000

Data Index: 375010 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3120. Min Act: -0.0000

Data Index: 666101 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3011. Min Act: -0.0001

Data Index: 564686 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3280. Min Act: -0.0000

Data Index: 314016 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1319738 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.2860. Min Act: -0.0000

Data Index: 92359 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.2949. Min Act: -0.0000

Data Index: 879856 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3059. Min Act: -0.0000

Data Index: 679850 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.2636. Min Act: -0.0000

Data Index: 519455 (C4 (Web Text))

Max Activating Token Index: 619