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

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

Neuron 4775 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.8734. Min Act: -0.0000

Data Index: 259904 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.8524. Min Act: -0.0000

Data Index: 349677 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.7964. Min Act: -0.0000

Data Index: 908461 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.6542. Min Act: -0.0000

Data Index: 369403 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.5085. Min Act: -0.0000

Data Index: 71232 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.4938. Min Act: -0.0000

Data Index: 77198 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.5977. Min Act: -0.0000

Data Index: 478115 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.5606. Min Act: -0.0000

Data Index: 625379 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.5602. Min Act: -0.0000

Data Index: 1270568 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.4446. Min Act: -0.0000

Data Index: 755242 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.5192. Min Act: -0.0000

Data Index: 432704 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.5760. Min Act: -0.0000

Data Index: 808600 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.2996. Min Act: -0.0000

Data Index: 325066 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.3601. Min Act: -0.0000

Data Index: 1237555 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.6333. Min Act: -0.0000

Data Index: 1006825 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.4304. Min Act: -0.0000

Data Index: 1290794 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.3534. Min Act: -0.0000

Data Index: 754899 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.4123. Min Act: -0.0000

Data Index: 146766 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.3167. Min Act: -0.0000

Data Index: 359098 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 1.8734. Min Range: -1.8734

Max Act: 1.3839. Min Act: -0.0000

Data Index: 87917 (C4 (Web Text))

Max Activating Token Index: 663