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

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

Neuron 3076 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0086. Min Act: -0.0003

Data Index: 1421485 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1566487 (Python Code)

Max Activating Token Index: 144

Text #2

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0082. Min Act: -0.0002

Data Index: 1581629 (Python Code)

Max Activating Token Index: 411

Text #3

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1557572 (Python Code)

Max Activating Token Index: 881

Text #4

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1527124 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0002

Data Index: 55083 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0074. Min Act: -0.0002

Data Index: 221247 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1308268 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1586131 (Python Code)

Max Activating Token Index: 221

Text #9

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1331250 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1046961 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1612136 (Python Code)

Max Activating Token Index: 248

Text #12

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1634476 (Python Code)

Max Activating Token Index: 385

Text #13

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1637230 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1535392 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0064. Min Act: -0.0003

Data Index: 759018 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1488535 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1309157 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0065. Min Act: -0.0002

Data Index: 316502 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1314849 (C4 (Web Text))

Max Activating Token Index: 757