Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4044 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1477835 (Python Code)

Max Activating Token Index: 181

Text #1

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0091. Min Act: -0.0002

Data Index: 402620 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1234989 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0081. Min Act: -0.0002

Data Index: 149441 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1611415 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1644425 (Python Code)

Max Activating Token Index: 391

Text #6

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0076. Min Act: -0.0002

Data Index: 107485 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0078. Min Act: -0.0002

Data Index: 568945 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1642027 (Python Code)

Max Activating Token Index: 294

Text #9

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0078. Min Act: -0.0002

Data Index: 127637 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0073. Min Act: -0.0002

Data Index: 1355628 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1569503 (Python Code)

Max Activating Token Index: 208

Text #12

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0070. Min Act: -0.0002

Data Index: 312554 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0071. Min Act: -0.0002

Data Index: 159077 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1265287 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1638123 (Python Code)

Max Activating Token Index: 172

Text #16

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0072. Min Act: -0.0002

Data Index: 97311 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0071. Min Act: -0.0002

Data Index: 112285 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0068. Min Act: -0.0002

Data Index: 563246 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0070. Min Act: -0.0002

Data Index: 650609 (C4 (Web Text))

Max Activating Token Index: 380