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

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

Neuron 382 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7233. Min Range: -3.7233

Max Act: 3.7233. Min Act: -0.0000

Data Index: 106750 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 3.7233. Min Range: -3.7233

Max Act: 3.3132. Min Act: -0.0000

Data Index: 864583 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 3.7233. Min Range: -3.7233

Max Act: 3.1964. Min Act: -0.0000

Data Index: 121852 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 3.7233. Min Range: -3.7233

Max Act: 3.0382. Min Act: -0.0000

Data Index: 254508 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.8775. Min Act: -0.0000

Data Index: 434425 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.8756. Min Act: -0.0000

Data Index: 803519 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 3.7233. Min Range: -3.7233

Max Act: 3.0021. Min Act: -0.0000

Data Index: 695231 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 3.7233. Min Range: -3.7233

Max Act: 3.0059. Min Act: -0.0000

Data Index: 737917 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.8550. Min Act: -0.0000

Data Index: 145393 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.6788. Min Act: -0.0000

Data Index: 835156 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.7148. Min Act: -0.0000

Data Index: 1073816 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.5785. Min Act: -0.0000

Data Index: 419537 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.5516. Min Act: -0.0000

Data Index: 1062570 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.6830. Min Act: -0.0000

Data Index: 903772 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.7760. Min Act: -0.0000

Data Index: 933012 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.6155. Min Act: -0.0000

Data Index: 490963 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.5826. Min Act: -0.0000

Data Index: 90684 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.5780. Min Act: -0.0000

Data Index: 1187286 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.5502. Min Act: -0.0000

Data Index: 557778 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 3.7233. Min Range: -3.7233

Max Act: 2.5304. Min Act: -0.0000

Data Index: 1284673 (C4 (Web Text))

Max Activating Token Index: 12