Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2128 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1182. Min Act: -0.0004

Data Index: 567002 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1094. Min Act: -0.0004

Data Index: 540495 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1091. Min Act: -0.0004

Data Index: 1253278 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1103. Min Act: -0.0004

Data Index: 435115 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1058. Min Act: -0.0004

Data Index: 846501 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1055. Min Act: -0.0004

Data Index: 1062113 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0978. Min Act: -0.0004

Data Index: 1535351 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1034. Min Act: -0.0004

Data Index: 827956 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0966. Min Act: -0.0004

Data Index: 95309 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0982. Min Act: -0.0004

Data Index: 157166 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0876. Min Act: -0.0004

Data Index: 325248 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1009. Min Act: -0.0004

Data Index: 262661 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1033. Min Act: -0.0004

Data Index: 23284 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1107. Min Act: -0.0004

Data Index: 1031043 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0913. Min Act: -0.0004

Data Index: 19659 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0978. Min Act: -0.0004

Data Index: 50044 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0908. Min Act: -0.0004

Data Index: 1011010 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0972. Min Act: -0.0004

Data Index: 681976 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0936. Min Act: -0.0004

Data Index: 590637 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0930. Min Act: -0.0004

Data Index: 1249279 (C4 (Web Text))

Max Activating Token Index: 47