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

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

Neuron 388 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.7000. Min Act: -0.0002

Data Index: 125343 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6955. Min Act: -0.0002

Data Index: 1210499 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6859. Min Act: -0.0002

Data Index: 481561 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6899. Min Act: -0.0002

Data Index: 824578 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6762. Min Act: -0.0002

Data Index: 1145444 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6687. Min Act: -0.0002

Data Index: 663141 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6790. Min Act: -0.0002

Data Index: 711404 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6750. Min Act: -0.0002

Data Index: 447501 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6784. Min Act: -0.0002

Data Index: 165780 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6772. Min Act: -0.0003

Data Index: 720233 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6813. Min Act: -0.0002

Data Index: 1333738 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6845. Min Act: -0.0002

Data Index: 516542 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6488. Min Act: -0.0002

Data Index: 396205 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6666. Min Act: -0.0002

Data Index: 1325956 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6638. Min Act: -0.0002

Data Index: 490245 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6652. Min Act: -0.0002

Data Index: 433305 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6592. Min Act: -0.0002

Data Index: 889634 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6465. Min Act: -0.0002

Data Index: 43559 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6523. Min Act: -0.0002

Data Index: 867144 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6673. Min Act: -0.0002

Data Index: 160546 (C4 (Web Text))

Max Activating Token Index: 373