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

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

Neuron 1375 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0121. Min Act: -0.0006

Data Index: 756990 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1345189 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0099. Min Act: -0.0006

Data Index: 937773 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0105. Min Act: -0.0006

Data Index: 605306 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0101. Min Act: -0.0006

Data Index: 48097 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0101. Min Act: -0.0006

Data Index: 544669 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1415596 (Python Code)

Max Activating Token Index: 601

Text #7

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0099. Min Act: -0.0006

Data Index: 139636 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1123105 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0088. Min Act: -0.0006

Data Index: 488835 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0102. Min Act: -0.0006

Data Index: 940754 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0095. Min Act: -0.0006

Data Index: 175148 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0092. Min Act: -0.0006

Data Index: 169969 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1607524 (Python Code)

Max Activating Token Index: 435

Text #14

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1042701 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0087. Min Act: -0.0006

Data Index: 460968 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1363493 (Python Code)

Max Activating Token Index: 787

Text #17

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1403705 (Python Code)

Max Activating Token Index: 1012

Text #18

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1648885 (Python Code)

Max Activating Token Index: 626

Text #19

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1239858 (C4 (Web Text))

Max Activating Token Index: 540