Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1328 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0005

Data Index: 524415 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0107. Min Act: -0.0005

Data Index: 146525 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0099. Min Act: -0.0004

Data Index: 255842 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0004

Data Index: 723181 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0004

Data Index: 788268 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0099. Min Act: -0.0004

Data Index: 1110264 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0096. Min Act: -0.0004

Data Index: 172912 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0096. Min Act: -0.0004

Data Index: 1000147 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0096. Min Act: -0.0004

Data Index: 1199372 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0094. Min Act: -0.0004

Data Index: 1256715 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0094. Min Act: -0.0004

Data Index: 831092 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0092. Min Act: -0.0004

Data Index: 118039 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0092. Min Act: -0.0004

Data Index: 261495 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0092. Min Act: -0.0004

Data Index: 90069 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0091. Min Act: -0.0004

Data Index: 531077 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0091. Min Act: -0.0005

Data Index: 477052 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0092. Min Act: -0.0004

Data Index: 1334952 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0092. Min Act: -0.0004

Data Index: 1482243 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0091. Min Act: -0.0004

Data Index: 933676 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0090. Min Act: -0.0004

Data Index: 113425 (C4 (Web Text))

Max Activating Token Index: 63