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

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

Neuron 3201 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1616719 (Python Code)

Max Activating Token Index: 358

Text #1

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1438650 (Python Code)

Max Activating Token Index: 325

Text #2

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1563983 (Python Code)

Max Activating Token Index: 138

Text #3

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1624609 (Python Code)

Max Activating Token Index: 990

Text #4

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1460893 (Python Code)

Max Activating Token Index: 998

Text #5

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1468179 (Python Code)

Max Activating Token Index: 176

Text #6

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1534988 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4159. Min Act: -0.0001

Data Index: 1589492 (Python Code)

Max Activating Token Index: 120

Text #8

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1627176 (Python Code)

Max Activating Token Index: 120

Text #9

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1590415 (Python Code)

Max Activating Token Index: 838

Text #10

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1397651 (Python Code)

Max Activating Token Index: 213

Text #11

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1578249 (Python Code)

Max Activating Token Index: 217

Text #12

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1369470 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1637262 (Python Code)

Max Activating Token Index: 153

Text #14

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1483275 (Python Code)

Max Activating Token Index: 125

Text #15

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1386428 (Python Code)

Max Activating Token Index: 163

Text #16

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1468771 (Python Code)

Max Activating Token Index: 747

Text #17

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1536485 (Python Code)

Max Activating Token Index: 779

Text #18

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1424964 (Python Code)

Max Activating Token Index: 330

Text #19

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1425175 (Python Code)

Max Activating Token Index: 806