Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2644 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0110. Min Act: -0.0002

Data Index: 69764 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1384296 (Python Code)

Max Activating Token Index: 538

Text #2

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1154242 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0083. Min Act: -0.0002

Data Index: 673745 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1136298 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0078. Min Act: -0.0002

Data Index: 845817 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1465760 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0077. Min Act: -0.0002

Data Index: 668150 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1223635 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0075. Min Act: -0.0002

Data Index: 582242 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0073. Min Act: -0.0002

Data Index: 135262 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1043305 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0071. Min Act: -0.0002

Data Index: 380104 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0074. Min Act: -0.0002

Data Index: 707863 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1383824 (Python Code)

Max Activating Token Index: 830

Text #15

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0071. Min Act: -0.0002

Data Index: 1556466 (Python Code)

Max Activating Token Index: 970

Text #16

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1579083 (Python Code)

Max Activating Token Index: 906

Text #17

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0073. Min Act: -0.0002

Data Index: 1428222 (Python Code)

Max Activating Token Index: 614

Text #18

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1083137 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0068. Min Act: -0.0002

Data Index: 84584 (C4 (Web Text))

Max Activating Token Index: 3