Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1081 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0100. Min Act: -0.0003

Data Index: 1360475 (Python Code)

Max Activating Token Index: 219

Text #1

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1528199 (Python Code)

Max Activating Token Index: 255

Text #2

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1615276 (Python Code)

Max Activating Token Index: 770

Text #3

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0090. Min Act: -0.0001

Data Index: 595677 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1489548 (Python Code)

Max Activating Token Index: 670

Text #5

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1506661 (Python Code)

Max Activating Token Index: 431

Text #6

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1544835 (Python Code)

Max Activating Token Index: 599

Text #7

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0086. Min Act: -0.0002

Data Index: 341075 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0087. Min Act: -0.0002

Data Index: 322011 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0086. Min Act: -0.0002

Data Index: 139368 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0082. Min Act: -0.0002

Data Index: 1537712 (Python Code)

Max Activating Token Index: 501

Text #11

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0080. Min Act: -0.0003

Data Index: 1541463 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0082. Min Act: -0.0002

Data Index: 248974 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1424908 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0079. Min Act: -0.0001

Data Index: 448945 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0080. Min Act: -0.0001

Data Index: 642655 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1506633 (Python Code)

Max Activating Token Index: 171

Text #17

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0080. Min Act: -0.0002

Data Index: 1609748 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1476022 (Python Code)

Max Activating Token Index: 913

Text #19

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0080. Min Act: -0.0002

Data Index: 480466 (C4 (Web Text))

Max Activating Token Index: 996