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

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

Neuron 3823 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0092. Min Act: -0.0002

Data Index: 843026 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0093. Min Act: -0.0002

Data Index: 487767 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1190314 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1440032 (Python Code)

Max Activating Token Index: 538

Text #4

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0080. Min Act: -0.0002

Data Index: 1129815 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0085. Min Act: -0.0002

Data Index: 46753 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0083. Min Act: -0.0002

Data Index: 583888 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0081. Min Act: -0.0002

Data Index: 616961 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0080. Min Act: -0.0002

Data Index: 1440174 (Python Code)

Max Activating Token Index: 969

Text #9

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1301297 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0076. Min Act: -0.0002

Data Index: 897266 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0075. Min Act: -0.0002

Data Index: 374071 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1397450 (Python Code)

Max Activating Token Index: 216

Text #13

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0075. Min Act: -0.0002

Data Index: 27728 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0073. Min Act: -0.0002

Data Index: 1470317 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0073. Min Act: -0.0002

Data Index: 429273 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0071. Min Act: -0.0002

Data Index: 775731 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1221700 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0071. Min Act: -0.0002

Data Index: 332337 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1015317 (C4 (Web Text))

Max Activating Token Index: 78