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

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

Neuron 48 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: 0.0086. Min Range: -0.0086

Max Act: 0.0086. Min Act: -0.0003

Data Index: 940246 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0083. Min Act: -0.0003

Data Index: 456417 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0080. Min Act: -0.0003

Data Index: 916231 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0077. Min Act: -0.0002

Data Index: 1463628 (Python Code)

Max Activating Token Index: 555

Text #4

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0074. Min Act: -0.0002

Data Index: 1513316 (Python Code)

Max Activating Token Index: 502

Text #5

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0076. Min Act: -0.0003

Data Index: 888978 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1522284 (Python Code)

Max Activating Token Index: 902

Text #7

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1183959 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0074. Min Act: -0.0002

Data Index: 1570864 (Python Code)

Max Activating Token Index: 545

Text #9

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0074. Min Act: -0.0003

Data Index: 222229 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0073. Min Act: -0.0003

Data Index: 312153 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0073. Min Act: -0.0003

Data Index: 283869 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0072. Min Act: -0.0003

Data Index: 370235 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1182685 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1613864 (Python Code)

Max Activating Token Index: 614

Text #15

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0073. Min Act: -0.0002

Data Index: 1534369 (Python Code)

Max Activating Token Index: 472

Text #16

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1210686 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0003

Data Index: 209401 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0003

Data Index: 443830 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0002

Data Index: 1554723 (Python Code)

Max Activating Token Index: 578