Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 536 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0131. Min Act: -0.0002

Data Index: 627227 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0110. Min Act: -0.0002

Data Index: 991202 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1041552 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0097. Min Act: -0.0002

Data Index: 460478 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0097. Min Act: -0.0002

Data Index: 581713 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0100. Min Act: -0.0002

Data Index: 936361 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0099. Min Act: -0.0002

Data Index: 976592 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0094. Min Act: -0.0002

Data Index: 601456 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0095. Min Act: -0.0002

Data Index: 527063 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1055657 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1072379 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0096. Min Act: -0.0002

Data Index: 492423 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0088. Min Act: -0.0002

Data Index: 969216 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1110512 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0090. Min Act: -0.0002

Data Index: 242090 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1060601 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1291598 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1634067 (Python Code)

Max Activating Token Index: 252

Text #18

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0088. Min Act: -0.0002

Data Index: 859560 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0093. Min Act: -0.0002

Data Index: 496510 (C4 (Web Text))

Max Activating Token Index: 1023