Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 434 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0097. Min Act: -0.0004

Data Index: 215397 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0093. Min Act: -0.0004

Data Index: 377965 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0095. Min Act: -0.0004

Data Index: 170045 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0099. Min Act: -0.0004

Data Index: 1556197 (Python Code)

Max Activating Token Index: 945

Text #4

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0092. Min Act: -0.0004

Data Index: 407503 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0094. Min Act: -0.0004

Data Index: 1064085 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0094. Min Act: -0.0004

Data Index: 396812 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0089. Min Act: -0.0004

Data Index: 705446 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0093. Min Act: -0.0004

Data Index: 451468 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0093. Min Act: -0.0004

Data Index: 463786 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0091. Min Act: -0.0004

Data Index: 759615 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0084. Min Act: -0.0004

Data Index: 183813 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0082. Min Act: -0.0004

Data Index: 1191593 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0086. Min Act: -0.0004

Data Index: 1601098 (Python Code)

Max Activating Token Index: 658

Text #14

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0088. Min Act: -0.0004

Data Index: 888767 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0073. Min Act: -0.0004

Data Index: 1320904 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0080. Min Act: -0.0004

Data Index: 1267660 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0088. Min Act: -0.0004

Data Index: 999591 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0093. Min Act: -0.0004

Data Index: 28499 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0081. Min Act: -0.0004

Data Index: 617771 (C4 (Web Text))

Max Activating Token Index: 976