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

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

Neuron 3066 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1203529 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1105457 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0088. Min Act: -0.0002

Data Index: 273115 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1037335 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0086. Min Act: -0.0002

Data Index: 486697 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0086. Min Act: -0.0002

Data Index: 637146 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0085. Min Act: -0.0002

Data Index: 160998 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0086. Min Act: -0.0002

Data Index: 785416 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0085. Min Act: -0.0002

Data Index: 32151 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0085. Min Act: -0.0002

Data Index: 971583 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1074088 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0083. Min Act: -0.0002

Data Index: 842602 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0083. Min Act: -0.0002

Data Index: 960969 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0082. Min Act: -0.0002

Data Index: 884729 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0082. Min Act: -0.0002

Data Index: 911536 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0080. Min Act: -0.0002

Data Index: 233425 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0081. Min Act: -0.0002

Data Index: 1463022 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0081. Min Act: -0.0002

Data Index: 785814 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0080. Min Act: -0.0002

Data Index: 694484 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0080. Min Act: -0.0002

Data Index: 180432 (C4 (Web Text))

Max Activating Token Index: 702