Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2135 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0095. Min Act: -0.0003

Data Index: 331942 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0003

Data Index: 1471045 (Python Code)

Max Activating Token Index: 140

Text #2

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0084. Min Act: -0.0003

Data Index: 604854 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1108645 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0088. Min Act: -0.0003

Data Index: 921665 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1619936 (Python Code)

Max Activating Token Index: 973

Text #6

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1286898 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1454174 (Python Code)

Max Activating Token Index: 776

Text #8

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1314187 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0073. Min Act: -0.0003

Data Index: 720565 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0070. Min Act: -0.0004

Data Index: 1035137 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0074. Min Act: -0.0003

Data Index: 859354 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1371458 (Python Code)

Max Activating Token Index: 716

Text #13

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0072. Min Act: -0.0003

Data Index: 564661 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0073. Min Act: -0.0003

Data Index: 251735 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1448977 (Python Code)

Max Activating Token Index: 412

Text #16

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0075. Min Act: -0.0003

Data Index: 840928 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0067. Min Act: -0.0003

Data Index: 793298 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0051. Min Act: -0.0003

Data Index: 125480 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0064. Min Act: -0.0003

Data Index: 961915 (C4 (Web Text))

Max Activating Token Index: 705