Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 323 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1319642 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0006

Data Index: 830628 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0005

Data Index: 90630 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1359075 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0006

Data Index: 784396 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0006

Data Index: 828180 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0006

Data Index: 1210084 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0006

Data Index: 122460 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0005

Data Index: 842304 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0006

Data Index: 978271 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1165897 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0006

Data Index: 294632 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0074. Min Act: -0.0006

Data Index: 792701 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1348233 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0006

Data Index: 417969 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0005

Data Index: 344862 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0005

Data Index: 1267361 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0005

Data Index: 1002359 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1042708 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0006

Data Index: 870422 (C4 (Web Text))

Max Activating Token Index: 234