Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 14 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.5615. Min Act: -0.0003

Data Index: 1420421 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.4168. Min Act: -0.0002

Data Index: 882670 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.4157. Min Act: -0.0002

Data Index: 904567 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.4198. Min Act: -0.0002

Data Index: 1133154 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.4152. Min Act: -0.0002

Data Index: 1589177 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3888. Min Act: -0.0003

Data Index: 1363133 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3903. Min Act: -0.0003

Data Index: 261879 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3839. Min Act: -0.0002

Data Index: 1552882 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3665. Min Act: -0.0003

Data Index: 1538285 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3822. Min Act: -0.0002

Data Index: 527162 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3795. Min Act: -0.0002

Data Index: 20325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3454. Min Act: -0.0002

Data Index: 1179980 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3611. Min Act: -0.0003

Data Index: 1259292 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3796. Min Act: -0.0003

Data Index: 1275945 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3771. Min Act: -0.0002

Data Index: 1554193 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3740. Min Act: -0.0002

Data Index: 633424 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3552. Min Act: -0.0003

Data Index: 1413113 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3739. Min Act: -0.0002

Data Index: 111950 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3579. Min Act: -0.0003

Data Index: 506807 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.5615. Min Range: -3.5615

Max Act: 3.3708. Min Act: -0.0002

Data Index: 488530 (C4 (Web Text))

Max Activating Token Index: 1023