Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1844 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0106. Min Act: -0.0002

Data Index: 114607 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1250188 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0086. Min Act: -0.0001

Data Index: 1523214 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0081. Min Act: -0.0002

Data Index: 281912 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0080. Min Act: -0.0002

Data Index: 1331717 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0078. Min Act: -0.0002

Data Index: 292111 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0077. Min Act: -0.0002

Data Index: 1318103 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0076. Min Act: -0.0001

Data Index: 1375549 (Python Code)

Max Activating Token Index: 49

Text #8

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0075. Min Act: -0.0002

Data Index: 220650 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0073. Min Act: -0.0002

Data Index: 429910 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0072. Min Act: -0.0002

Data Index: 918956 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1593728 (Python Code)

Max Activating Token Index: 366

Text #12

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1163008 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0071. Min Act: -0.0002

Data Index: 313593 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0070. Min Act: -0.0001

Data Index: 1414198 (Python Code)

Max Activating Token Index: 883

Text #15

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1100682 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0070. Min Act: -0.0002

Data Index: 24364 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0068. Min Act: -0.0002

Data Index: 256319 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0069. Min Act: -0.0002

Data Index: 728029 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0069. Min Act: -0.0001

Data Index: 1492614 (Python Code)

Max Activating Token Index: 20