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

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

Neuron 5415 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: 0.5903. Min Range: -0.5903

Max Act: 0.5903. Min Act: -0.0002

Data Index: 668194 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5662. Min Act: -0.0002

Data Index: 1059436 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5610. Min Act: -0.0002

Data Index: 877094 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5493. Min Act: -0.0002

Data Index: 1276825 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5437. Min Act: -0.0002

Data Index: 1256757 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5450. Min Act: -0.0002

Data Index: 589321 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5461. Min Act: -0.0002

Data Index: 309657 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5330. Min Act: -0.0002

Data Index: 896118 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5199. Min Act: -0.0002

Data Index: 573601 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5199. Min Act: -0.0002

Data Index: 723649 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5204. Min Act: -0.0002

Data Index: 310863 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5291. Min Act: -0.0002

Data Index: 143326 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5046. Min Act: -0.0002

Data Index: 739042 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5068. Min Act: -0.0002

Data Index: 97375 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.4953. Min Act: -0.0002

Data Index: 456158 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.4970. Min Act: -0.0002

Data Index: 1216616 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5086. Min Act: -0.0002

Data Index: 1039403 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5006. Min Act: -0.0002

Data Index: 1218649 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.4950. Min Act: -0.0002

Data Index: 1332675 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.4971. Min Act: -0.0002

Data Index: 14117 (C4 (Web Text))

Max Activating Token Index: 302